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

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

Neuron 5538 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1814. Min Act: -0.0002

Data Index: 1088107 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1885. Min Act: -0.0002

Data Index: 491103 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1593546 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1288. Min Act: -0.0002

Data Index: 573549 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1468. Min Act: -0.0002

Data Index: 819593 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1378643 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1260. Min Act: -0.0002

Data Index: 492099 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1279. Min Act: -0.0002

Data Index: 47884 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1156233 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1257. Min Act: -0.0002

Data Index: 344861 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1251. Min Act: -0.0002

Data Index: 299577 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1187. Min Act: -0.0002

Data Index: 895339 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1183. Min Act: -0.0002

Data Index: 896256 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1519597 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1104. Min Act: -0.0002

Data Index: 273997 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1197. Min Act: -0.0002

Data Index: 972130 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1084. Min Act: -0.0002

Data Index: 671870 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1310444 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1172. Min Act: -0.0002

Data Index: 575521 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1123. Min Act: -0.0002

Data Index: 754168 (C4 (Web Text))

Max Activating Token Index: 717