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

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

Neuron 120 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.4828. Min Act: -0.0000

Data Index: 979793 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.4755. Min Act: -0.0000

Data Index: 706960 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.4109. Min Act: -0.0000

Data Index: 390014 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3921. Min Act: -0.0000

Data Index: 586248 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.4098. Min Act: -0.0000

Data Index: 170183 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.4062. Min Act: -0.0000

Data Index: 915886 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3755. Min Act: -0.0000

Data Index: 503461 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1150898 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3696. Min Act: -0.0000

Data Index: 551013 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3575. Min Act: -0.0000

Data Index: 601155 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1027844 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1345101 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1226075 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3467. Min Act: -0.0000

Data Index: 792220 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3363. Min Act: -0.0000

Data Index: 60707 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3496. Min Act: -0.0000

Data Index: 290777 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3422. Min Act: -0.0000

Data Index: 405186 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1156228 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1131555 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1294573 (C4 (Web Text))

Max Activating Token Index: 215