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

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

Neuron 2001 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1019211 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1176. Min Act: -0.0001

Data Index: 102408 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1127215 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1222969 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1131. Min Act: -0.0001

Data Index: 241875 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1169. Min Act: -0.0001

Data Index: 220021 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1218. Min Act: -0.0001

Data Index: 896856 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1308131 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1144. Min Act: -0.0001

Data Index: 662180 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1175. Min Act: -0.0001

Data Index: 155088 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1132. Min Act: -0.0001

Data Index: 681459 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1101. Min Act: -0.0001

Data Index: 471008 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1074. Min Act: -0.0001

Data Index: 328181 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1162. Min Act: -0.0001

Data Index: 904922 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1200. Min Act: -0.0001

Data Index: 390152 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1106. Min Act: -0.0001

Data Index: 547621 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1045525 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1109. Min Act: -0.0001

Data Index: 307403 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1010508 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1156766 (C4 (Web Text))

Max Activating Token Index: 610