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

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

Neuron 3569 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.9966. Min Act: -0.0001

Data Index: 657905 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.9941. Min Act: -0.0001

Data Index: 229908 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2253. Min Act: -0.0001

Data Index: 248226 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.0968. Min Act: -0.0001

Data Index: 250883 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.9257. Min Act: -0.0001

Data Index: 862759 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.9340. Min Act: -0.0001

Data Index: 527658 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.3320. Min Act: -0.0001

Data Index: 645561 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.9160. Min Act: -0.0001

Data Index: 1016125 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.0222. Min Act: -0.0001

Data Index: 37761 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.0004. Min Act: -0.0001

Data Index: 757421 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.8683. Min Act: -0.0001

Data Index: 414547 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.9397. Min Act: -0.0001

Data Index: 66027 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.1096. Min Act: -0.0001

Data Index: 702744 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.9324. Min Act: -0.0001

Data Index: 943010 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.9050. Min Act: -0.0001

Data Index: 1207519 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.7935. Min Act: -0.0001

Data Index: 1329720 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.6387. Min Act: -0.0001

Data Index: 182529 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.8695. Min Act: -0.0001

Data Index: 594882 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.8223. Min Act: -0.0001

Data Index: 607799 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 3.3320. Min Range: -3.3320

Max Act: 2.6901. Min Act: -0.0001

Data Index: 3071 (C4 (Web Text))

Max Activating Token Index: 570