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

Dataset: The Pile

Neuron 3339 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.5349. Min Act: -0.0000

Data Index: 689526 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.4468. Min Act: -0.0000

Data Index: 1136413 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3981. Min Act: -0.0000

Data Index: 1890816 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2060. Min Act: -0.0000

Data Index: 272634 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.9983. Min Act: -0.0000

Data Index: 625746 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.9983. Min Act: -0.0000

Data Index: 986970 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.1117. Min Act: -0.0000

Data Index: 232268 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.0283. Min Act: -0.0000

Data Index: 414000 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.8725. Min Act: -0.0000

Data Index: 1520172 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.9835. Min Act: -0.0000

Data Index: 364169 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.9604. Min Act: -0.0000

Data Index: 436554 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.7471. Min Act: -0.0000

Data Index: 88820 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.8252. Min Act: -0.0000

Data Index: 295356 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.7623. Min Act: -0.0000

Data Index: 1793419 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.5897. Min Act: -0.0000

Data Index: 432903 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.7177. Min Act: -0.0000

Data Index: 350168 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.8552. Min Act: -0.0000

Data Index: 265278 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.5183. Min Act: -0.0000

Data Index: 1182537 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.5080. Min Act: -0.0000

Data Index: 1032882 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 3.5349. Min Range: -3.5349

Max Act: 2.5233. Min Act: -0.0000

Data Index: 1065589 (The Pile)

Max Activating Token Index: 399