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

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

Neuron 3104 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: 0.2619. Min Range: -0.2619

Max Act: 0.2510. Min Act: -0.0002

Data Index: 222817 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2619. Min Act: -0.0002

Data Index: 502220 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2288. Min Act: -0.0002

Data Index: 594304 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2472. Min Act: -0.0002

Data Index: 936722 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2338. Min Act: -0.0002

Data Index: 768981 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2363. Min Act: -0.0002

Data Index: 348042 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2385. Min Act: -0.0002

Data Index: 888906 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2298. Min Act: -0.0002

Data Index: 13516 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2322. Min Act: -0.0002

Data Index: 756315 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2193. Min Act: -0.0002

Data Index: 758698 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2027. Min Act: -0.0002

Data Index: 1216217 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2224. Min Act: -0.0002

Data Index: 1143039 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2359. Min Act: -0.0002

Data Index: 548515 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2207. Min Act: -0.0002

Data Index: 809759 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2034. Min Act: -0.0002

Data Index: 378397 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2100. Min Act: -0.0002

Data Index: 252550 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2175. Min Act: -0.0002

Data Index: 227625 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2138. Min Act: -0.0002

Data Index: 1107057 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2202. Min Act: -0.0002

Data Index: 1313923 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2143. Min Act: -0.0002

Data Index: 1208856 (C4 (Web Text))

Max Activating Token Index: 892