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

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

Neuron 2211 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0004

Data Index: 1138369 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0396. Min Act: -0.0004

Data Index: 176386 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0403. Min Act: -0.0004

Data Index: 182903 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0418. Min Act: -0.0004

Data Index: 432840 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0396. Min Act: -0.0004

Data Index: 730641 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0383. Min Act: -0.0004

Data Index: 1293391 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0383. Min Act: -0.0004

Data Index: 877010 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0348. Min Act: -0.0004

Data Index: 697302 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0362. Min Act: -0.0004

Data Index: 856650 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0353. Min Act: -0.0004

Data Index: 235049 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0358. Min Act: -0.0004

Data Index: 1224700 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0347. Min Act: -0.0004

Data Index: 618303 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0348. Min Act: -0.0004

Data Index: 954141 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0359. Min Act: -0.0004

Data Index: 1217791 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0340. Min Act: -0.0004

Data Index: 972899 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0332. Min Act: -0.0004

Data Index: 238723 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0324. Min Act: -0.0004

Data Index: 997915 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0326. Min Act: -0.0004

Data Index: 1318335 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0348. Min Act: -0.0004

Data Index: 320637 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1244331 (C4 (Web Text))

Max Activating Token Index: 296