Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 29 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.5020. Min Act: -0.0000

Data Index: 805896 (The Pile)

Max Activating Token Index: 777

Text #1

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4731. Min Act: -0.0000

Data Index: 437951 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1259039 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1771372 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1439135 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1776002 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1739728 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1318814 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1758617 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3967. Min Act: -0.0000

Data Index: 221772 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4247. Min Act: -0.0000

Data Index: 873370 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1661087 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3748. Min Act: -0.0000

Data Index: 45318 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1057872 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4031. Min Act: -0.0000

Data Index: 209560 (The Pile)

Max Activating Token Index: 939

Text #15

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3900. Min Act: -0.0000

Data Index: 435225 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4038. Min Act: -0.0000

Data Index: 611788 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1661503 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1113884 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1644091 (The Pile)

Max Activating Token Index: 738