Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.1795. Min Act: -0.0000

Data Index: 793375 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1154338 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.0796. Min Act: -0.0000

Data Index: 661739 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.9381. Min Act: -0.0000

Data Index: 354469 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.9207. Min Act: -0.0000

Data Index: 685041 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1256800 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8298. Min Act: -0.0000

Data Index: 190099 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1189207 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8141. Min Act: -0.0000

Data Index: 174437 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8322. Min Act: -0.0000

Data Index: 799540 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8205. Min Act: -0.0000

Data Index: 473066 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8154. Min Act: -0.0000

Data Index: 739991 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8035. Min Act: -0.0000

Data Index: 176109 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8101. Min Act: -0.0000

Data Index: 323290 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8295. Min Act: -0.0000

Data Index: 590942 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8030. Min Act: -0.0000

Data Index: 362115 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.7704. Min Act: -0.0000

Data Index: 400723 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.7749. Min Act: -0.0000

Data Index: 967184 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1348453 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.7496. Min Act: -0.0000

Data Index: 60080 (C4 (Web Text))

Max Activating Token Index: 676