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

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

Neuron 5989 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3355. Min Range: -6.3355

Max Act: 6.3166. Min Act: -0.0000

Data Index: 800889 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 6.3355. Min Range: -6.3355

Max Act: 6.3355. Min Act: -0.0000

Data Index: 885902 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 6.3355. Min Range: -6.3355

Max Act: 6.0199. Min Act: -0.0000

Data Index: 333785 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 6.3355. Min Range: -6.3355

Max Act: 5.3372. Min Act: -0.0000

Data Index: 1255849 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 6.3355. Min Range: -6.3355

Max Act: 5.0493. Min Act: -0.0000

Data Index: 627379 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.2981. Min Act: -0.0000

Data Index: 597744 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.6938. Min Act: -0.0000

Data Index: 1222650 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.5904. Min Act: -0.0000

Data Index: 318926 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.2902. Min Act: -0.0000

Data Index: 1263381 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.4678. Min Act: -0.0000

Data Index: 597762 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.5031. Min Act: -0.0000

Data Index: 987708 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.6343. Min Act: -0.0000

Data Index: 789145 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.0198. Min Act: -0.0000

Data Index: 848411 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.4687. Min Act: -0.0000

Data Index: 829950 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 6.3355. Min Range: -6.3355

Max Act: 3.9440. Min Act: -0.0000

Data Index: 1326342 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 6.3355. Min Range: -6.3355

Max Act: 3.5429. Min Act: -0.0000

Data Index: 536196 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 6.3355. Min Range: -6.3355

Max Act: 3.9017. Min Act: -0.0000

Data Index: 1116409 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 6.3355. Min Range: -6.3355

Max Act: 4.0138. Min Act: -0.0000

Data Index: 641512 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 6.3355. Min Range: -6.3355

Max Act: 3.5183. Min Act: -0.0000

Data Index: 1312024 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 6.3355. Min Range: -6.3355

Max Act: 3.7826. Min Act: -0.0000

Data Index: 1124084 (C4 (Web Text))

Max Activating Token Index: 281