Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2033 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1336. Min Act: -0.0002

Data Index: 784331 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1272. Min Act: -0.0002

Data Index: 995967 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1242. Min Act: -0.0001

Data Index: 987492 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1171. Min Act: -0.0002

Data Index: 740460 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1192. Min Act: -0.0002

Data Index: 33836 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1171. Min Act: -0.0002

Data Index: 1247986 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1174. Min Act: -0.0002

Data Index: 83239 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1212. Min Act: -0.0002

Data Index: 12743 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1124. Min Act: -0.0002

Data Index: 104004 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1090. Min Act: -0.0002

Data Index: 333 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1068760 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1106. Min Act: -0.0001

Data Index: 507126 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1274228 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1145. Min Act: -0.0002

Data Index: 82278 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1100. Min Act: -0.0002

Data Index: 424903 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1279228 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1136. Min Act: -0.0002

Data Index: 554954 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1131. Min Act: -0.0002

Data Index: 291233 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1119. Min Act: -0.0002

Data Index: 390646 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1086. Min Act: -0.0002

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 240