< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 23 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.8345. Min Act: -0.0004

Data Index: 1241226 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.8805. Min Act: -0.0004

Data Index: 1856757 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.8002. Min Act: -0.0004

Data Index: 1005719 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7731. Min Act: -0.0004

Data Index: 1849570 (The Pile)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7384. Min Act: -0.0004

Data Index: 265169 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7403. Min Act: -0.0004

Data Index: 1431649 (The Pile)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7327. Min Act: -0.0004

Data Index: 1122028 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7499. Min Act: -0.0004

Data Index: 1912127 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7476. Min Act: -0.0004

Data Index: 14092 (The Pile)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7221. Min Act: -0.0004

Data Index: 1456335 (The Pile)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7674. Min Act: -0.0004

Data Index: 1556604 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7041. Min Act: -0.0004

Data Index: 803716 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6782. Min Act: -0.0004

Data Index: 1209645 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7447. Min Act: -0.0004

Data Index: 467085 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6322. Min Act: -0.0004

Data Index: 1809246 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6967. Min Act: -0.0004

Data Index: 175707 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6907. Min Act: -0.0004

Data Index: 1259233 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6924. Min Act: -0.0004

Data Index: 1698121 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7397. Min Act: -0.0004

Data Index: 631050 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6873. Min Act: -0.0004

Data Index: 1114776 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #19