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

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

Neuron 2668 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: 4.3223. Min Range: -4.3223

Max Act: 4.3223. Min Act: -0.0000

Data Index: 806028 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9536. Min Act: -0.0000

Data Index: 486863 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.8747. Min Act: -0.0000

Data Index: 1141356 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.0141. Min Act: -0.0000

Data Index: 894623 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9060. Min Act: -0.0000

Data Index: 121862 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.6902. Min Act: -0.0000

Data Index: 692136 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.6763. Min Act: -0.0000

Data Index: 405285 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.5464. Min Act: -0.0000

Data Index: 1327839 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.4341. Min Act: -0.0000

Data Index: 756666 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.5988. Min Act: -0.0000

Data Index: 949427 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.5504. Min Act: -0.0000

Data Index: 899827 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.3915. Min Act: -0.0000

Data Index: 968647 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.2060. Min Act: -0.0000

Data Index: 95386 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.3259. Min Act: -0.0000

Data Index: 812042 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.3567. Min Act: -0.0000

Data Index: 727560 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.5447. Min Act: -0.0000

Data Index: 308606 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.3207. Min Act: -0.0000

Data Index: 573460 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.2897. Min Act: -0.0000

Data Index: 968214 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.6379. Min Act: -0.0000

Data Index: 468442 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.4521. Min Act: -0.0000

Data Index: 605108 (C4 (Web Text))

Max Activating Token Index: 626