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

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

Neuron 3961 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: 0.9383. Min Range: -0.9383

Max Act: 0.9383. Min Act: -0.0002

Data Index: 369613 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8274. Min Act: -0.0002

Data Index: 587253 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8580. Min Act: -0.0002

Data Index: 1255186 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8360. Min Act: -0.0002

Data Index: 415952 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8271. Min Act: -0.0002

Data Index: 1530557 (Python Code)

Max Activating Token Index: 460

Text #5

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8072. Min Act: -0.0002

Data Index: 605489 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7766. Min Act: -0.0002

Data Index: 397559 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7515. Min Act: -0.0002

Data Index: 418209 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8227. Min Act: -0.0002

Data Index: 730301 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7711. Min Act: -0.0002

Data Index: 1452796 (Python Code)

Max Activating Token Index: 178

Text #10

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8191. Min Act: -0.0002

Data Index: 686848 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7806. Min Act: -0.0002

Data Index: 277404 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7816. Min Act: -0.0002

Data Index: 204328 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7801. Min Act: -0.0002

Data Index: 1566161 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8212. Min Act: -0.0002

Data Index: 736679 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.6801. Min Act: -0.0002

Data Index: 85952 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7697. Min Act: -0.0002

Data Index: 509607 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.6884. Min Act: -0.0002

Data Index: 731674 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7893. Min Act: -0.0002

Data Index: 201879 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7368. Min Act: -0.0002

Data Index: 417805 (C4 (Web Text))

Max Activating Token Index: 367