Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2981 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3971. Min Act: -0.0003

Data Index: 1099511 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3832. Min Act: -0.0003

Data Index: 198606 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3753. Min Act: -0.0003

Data Index: 907698 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3437. Min Act: -0.0003

Data Index: 173046 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3563. Min Act: -0.0003

Data Index: 387854 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3534. Min Act: -0.0003

Data Index: 38479 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3379. Min Act: -0.0003

Data Index: 323564 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3353. Min Act: -0.0003

Data Index: 403637 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3124. Min Act: -0.0003

Data Index: 1148526 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3363. Min Act: -0.0003

Data Index: 708719 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3223. Min Act: -0.0003

Data Index: 1290917 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3195. Min Act: -0.0003

Data Index: 41101 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3020. Min Act: -0.0003

Data Index: 1008203 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3125. Min Act: -0.0003

Data Index: 413996 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3128. Min Act: -0.0003

Data Index: 161538 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2993. Min Act: -0.0003

Data Index: 347470 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3199. Min Act: -0.0003

Data Index: 562959 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2763. Min Act: -0.0003

Data Index: 1288279 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3098. Min Act: -0.0003

Data Index: 845644 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3075. Min Act: -0.0003

Data Index: 1010041 (C4 (Web Text))

Max Activating Token Index: 420