Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 893 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1563546 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1404. Min Act: -0.0001

Data Index: 278333 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1626848 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1055780 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1005777 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1036127 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1189. Min Act: -0.0001

Data Index: 201379 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1349672 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1340229 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1319. Min Act: -0.0001

Data Index: 697574 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1216. Min Act: -0.0001

Data Index: 321814 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1243451 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1079226 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1154. Min Act: -0.0001

Data Index: 280950 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1533693 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1241. Min Act: -0.0001

Data Index: 589503 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1180. Min Act: -0.0001

Data Index: 691706 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1227. Min Act: -0.0000

Data Index: 660402 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1417013 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1124. Min Act: -0.0000

Data Index: 504286 (C4 (Web Text))

Max Activating Token Index: 554