< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 26 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: 0.7835. Min Range: -0.7835

Max Act: 0.7835. Min Act: -0.0004

Data Index: 497834 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7709. Min Act: -0.0004

Data Index: 1625302 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7831. Min Act: -0.0004

Data Index: 1295868 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7000. Min Act: -0.0004

Data Index: 266152 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6867. Min Act: -0.0004

Data Index: 1189177 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7076. Min Act: -0.0004

Data Index: 606082 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6925. Min Act: -0.0004

Data Index: 1456479 (The Pile)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6650. Min Act: -0.0004

Data Index: 395602 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6859. Min Act: -0.0004

Data Index: 294896 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6845. Min Act: -0.0004

Data Index: 222919 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5746. Min Act: -0.0004

Data Index: 1984554 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7223. Min Act: -0.0004

Data Index: 1142102 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6352. Min Act: -0.0004

Data Index: 310588 (The Pile)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6578. Min Act: -0.0004

Data Index: 1553996 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7237. Min Act: -0.0004

Data Index: 1614151 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6750. Min Act: -0.0004

Data Index: 1093757 (The Pile)

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6694. Min Act: -0.0004

Data Index: 332279 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6448. Min Act: -0.0004

Data Index: 1457242 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6461. Min Act: -0.0004

Data Index: 1285330 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6862. Min Act: -0.0004

Data Index: 1139388 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #19