< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4085 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.9989. Min Act: -0.0001

Data Index: 716814 (The Pile)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.9002. Min Act: -0.0001

Data Index: 1965307 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0047. Min Act: -0.0001

Data Index: 594888 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8980. Min Act: -0.0001

Data Index: 1560378 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1428081 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8890. Min Act: -0.0001

Data Index: 1684651 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0461. Min Act: -0.0001

Data Index: 242920 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.9822. Min Act: -0.0001

Data Index: 156207 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8293. Min Act: -0.0001

Data Index: 959828 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8713. Min Act: -0.0001

Data Index: 1304414 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8331. Min Act: -0.0001

Data Index: 1607064 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.9110. Min Act: -0.0001

Data Index: 1001629 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8795. Min Act: -0.0001

Data Index: 1591277 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8453. Min Act: -0.0001

Data Index: 854153 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7899. Min Act: -0.0001

Data Index: 160883 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7742. Min Act: -0.0001

Data Index: 752167 (The Pile)

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8004. Min Act: -0.0001

Data Index: 371853 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7426. Min Act: -0.0001

Data Index: 639995 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.6808. Min Act: -0.0001

Data Index: 417852 (The Pile)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8003. Min Act: -0.0001

Data Index: 294566 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #19