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

Dataset: The Pile

Neuron 1410 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4434. Min Act: -0.0000

Data Index: 230983 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4008. Min Act: -0.0000

Data Index: 861177 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1471213 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1302571 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3556. Min Act: -0.0000

Data Index: 169054 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3444. Min Act: -0.0000

Data Index: 933196 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3535. Min Act: -0.0000

Data Index: 394526 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1761501 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3376. Min Act: -0.0000

Data Index: 32804 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3526. Min Act: -0.0000

Data Index: 786613 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1547354 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3449. Min Act: -0.0000

Data Index: 51115 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1543935 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1835593 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1210733 (The Pile)

Max Activating Token Index: 376

Text #15

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1392760 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3287. Min Act: -0.0000

Data Index: 587361 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3085. Min Act: -0.0000

Data Index: 171986 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3111. Min Act: -0.0000

Data Index: 912558 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1611091 (The Pile)

Max Activating Token Index: 103