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

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

Neuron 3652 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.5758. Min Act: -0.0000

Data Index: 914846 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.4077. Min Act: -0.0000

Data Index: 420312 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.5977. Min Act: -0.0000

Data Index: 1187727 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.2342. Min Act: -0.0000

Data Index: 216199 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.2312. Min Act: -0.0000

Data Index: 1165920 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.4805. Min Act: -0.0000

Data Index: 777062 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.2768. Min Act: -0.0000

Data Index: 1185018 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.2950. Min Act: -0.0000

Data Index: 735872 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.2177. Min Act: -0.0000

Data Index: 688068 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.1516. Min Act: -0.0000

Data Index: 683706 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.0973. Min Act: -0.0000

Data Index: 235435 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.9292. Min Act: -0.0000

Data Index: 929093 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.7216. Min Act: -0.0000

Data Index: 503359 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.8414. Min Act: -0.0000

Data Index: 19034 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.7529. Min Act: -0.0000

Data Index: 54379 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.5592. Min Act: -0.0000

Data Index: 216468 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.6780. Min Act: -0.0000

Data Index: 993723 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.8105. Min Act: -0.0000

Data Index: 728486 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.6581. Min Act: -0.0000

Data Index: 747121 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.4843. Min Act: -0.0000

Data Index: 620260 (C4 (Web Text))

Max Activating Token Index: 733