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

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

Neuron 6012 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: 2.0237. Min Range: -2.0237

Max Act: 1.7587. Min Act: -0.0000

Data Index: 34770 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.8385. Min Act: -0.0000

Data Index: 1166876 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.8343. Min Act: -0.0000

Data Index: 1097167 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.8184. Min Act: -0.0000

Data Index: 606839 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 2.0237. Min Range: -2.0237

Max Act: 2.0237. Min Act: -0.0000

Data Index: 1336192 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.7333. Min Act: -0.0000

Data Index: 98941 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.7441. Min Act: -0.0000

Data Index: 240050 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.7431. Min Act: -0.0000

Data Index: 1083894 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1003524 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.5467. Min Act: -0.0000

Data Index: 417293 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.5180. Min Act: -0.0000

Data Index: 132748 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.4171. Min Act: -0.0000

Data Index: 323723 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.5807. Min Act: -0.0000

Data Index: 418463 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.4184. Min Act: -0.0000

Data Index: 778071 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.4213. Min Act: -0.0000

Data Index: 816949 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.3706. Min Act: -0.0000

Data Index: 1125763 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.3666. Min Act: -0.0000

Data Index: 525853 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.4458. Min Act: -0.0000

Data Index: 1271749 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.3493. Min Act: -0.0000

Data Index: 519177 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 2.0237. Min Range: -2.0237

Max Act: 1.2695. Min Act: -0.0000

Data Index: 433803 (C4 (Web Text))

Max Activating Token Index: 277