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

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

Neuron 4212 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2666. Min Act: -0.0001

Data Index: 1289321 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1026067 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2490. Min Act: -0.0001

Data Index: 97858 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2397. Min Act: -0.0001

Data Index: 1271247 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2084. Min Act: -0.0001

Data Index: 510936 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2303. Min Act: -0.0001

Data Index: 61377 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2285. Min Act: -0.0001

Data Index: 968505 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2156. Min Act: -0.0001

Data Index: 418968 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2142. Min Act: -0.0001

Data Index: 594492 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1125152 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2216. Min Act: -0.0001

Data Index: 579073 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2320. Min Act: -0.0001

Data Index: 804940 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1054775 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1314438 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1993. Min Act: -0.0001

Data Index: 822509 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1945. Min Act: -0.0001

Data Index: 75799 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2260. Min Act: -0.0001

Data Index: 764624 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1998. Min Act: -0.0000

Data Index: 906408 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2058. Min Act: -0.0000

Data Index: 905431 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1147087 (C4 (Web Text))

Max Activating Token Index: 275