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

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

Neuron 4363 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.4623. Min Act: -0.0000

Data Index: 688312 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2726. Min Act: -0.0000

Data Index: 896206 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1243 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2783. Min Act: -0.0001

Data Index: 690146 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2258. Min Act: -0.0000

Data Index: 340866 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2444. Min Act: -0.0000

Data Index: 439590 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1159818 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2345. Min Act: -0.0001

Data Index: 286135 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2685. Min Act: -0.0000

Data Index: 563467 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2334. Min Act: -0.0000

Data Index: 249314 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1340617 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2060. Min Act: -0.0000

Data Index: 742176 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1358774 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2271. Min Act: -0.0000

Data Index: 468816 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1294933 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2185. Min Act: -0.0000

Data Index: 19896 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.1934. Min Act: -0.0000

Data Index: 382454 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1028193 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2086. Min Act: -0.0000

Data Index: 770478 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2115. Min Act: -0.0000

Data Index: 515723 (C4 (Web Text))

Max Activating Token Index: 460