Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.8959. Min Act: -0.0000

Data Index: 498000 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 3.0415. Min Range: -3.0415

Max Act: 3.0415. Min Act: -0.0000

Data Index: 991996 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.8038. Min Act: -0.0000

Data Index: 1201207 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.9289. Min Act: -0.0000

Data Index: 203110 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.6606. Min Act: -0.0000

Data Index: 106390 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.6355. Min Act: -0.0000

Data Index: 478929 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.5935. Min Act: -0.0000

Data Index: 1078416 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.7017. Min Act: -0.0000

Data Index: 376601 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.4296. Min Act: -0.0000

Data Index: 1072330 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.2802. Min Act: -0.0000

Data Index: 1339371 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.4883. Min Act: -0.0000

Data Index: 177921 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.2439. Min Act: -0.0000

Data Index: 807024 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.5934. Min Act: -0.0000

Data Index: 423526 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.4485. Min Act: -0.0000

Data Index: 451729 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.0475. Min Act: -0.0000

Data Index: 161767 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 3.0415. Min Range: -3.0415

Max Act: 1.9211. Min Act: -0.0000

Data Index: 436230 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.2948. Min Act: -0.0000

Data Index: 1226048 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.2579. Min Act: -0.0000

Data Index: 382849 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.1257. Min Act: -0.0000

Data Index: 868807 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 3.0415. Min Range: -3.0415

Max Act: 2.0966. Min Act: -0.0000

Data Index: 824270 (C4 (Web Text))

Max Activating Token Index: 1010