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

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

Neuron 4721 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.2773. Min Act: -0.0002

Data Index: 822807 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.1903. Min Act: -0.0002

Data Index: 881303 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.2920. Min Act: -0.0002

Data Index: 13694 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.3727. Min Act: -0.0002

Data Index: 1304603 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.3205. Min Act: -0.0002

Data Index: 1004939 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.3128. Min Act: -0.0002

Data Index: 928559 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.1216. Min Act: -0.0002

Data Index: 1191646 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.2719. Min Act: -0.0002

Data Index: 772652 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.1256. Min Act: -0.0002

Data Index: 1149452 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.0948. Min Act: -0.0002

Data Index: 322149 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.0794. Min Act: -0.0002

Data Index: 457432 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.4096. Min Act: -0.0002

Data Index: 1020958 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.1524. Min Act: -0.0002

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 4.4096. Min Range: -4.4096

Max Act: 3.8399. Min Act: -0.0002

Data Index: 1335614 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.1431. Min Act: -0.0002

Data Index: 391624 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.1070. Min Act: -0.0002

Data Index: 225481 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.1220. Min Act: -0.0002

Data Index: 114392 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 4.4096. Min Range: -4.4096

Max Act: 3.9228. Min Act: -0.0002

Data Index: 349027 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 4.4096. Min Range: -4.4096

Max Act: 3.9514. Min Act: -0.0002

Data Index: 453338 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 4.4096. Min Range: -4.4096

Max Act: 4.0924. Min Act: -0.0002

Data Index: 1211303 (C4 (Web Text))

Max Activating Token Index: 344