Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1298 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2906. Min Act: -0.0000

Data Index: 896407 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1137396 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2672. Min Act: -0.0000

Data Index: 369744 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1145465 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2127. Min Act: -0.0000

Data Index: 224464 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2336. Min Act: -0.0000

Data Index: 58791 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2266. Min Act: -0.0000

Data Index: 703322 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2061. Min Act: -0.0000

Data Index: 881699 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2369. Min Act: -0.0000

Data Index: 179367 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2108. Min Act: -0.0000

Data Index: 908052 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2193. Min Act: -0.0000

Data Index: 854701 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2157. Min Act: -0.0000

Data Index: 470935 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2057. Min Act: -0.0000

Data Index: 294999 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2025. Min Act: -0.0000

Data Index: 22696 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1854. Min Act: -0.0000

Data Index: 674161 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1152915 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2041. Min Act: -0.0000

Data Index: 843630 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1289902 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1911. Min Act: -0.0000

Data Index: 718899 (C4 (Web Text))

Max Activating Token Index: 612