Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1259 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1378. Min Act: -0.0001

Data Index: 327869 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1279. Min Act: -0.0001

Data Index: 871073 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1419. Min Act: -0.0001

Data Index: 747134 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1062602 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1330841 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1313. Min Act: -0.0001

Data Index: 84200 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1303. Min Act: -0.0001

Data Index: 322035 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1307. Min Act: -0.0001

Data Index: 141596 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1224. Min Act: -0.0001

Data Index: 660956 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1243. Min Act: -0.0001

Data Index: 8270 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1223. Min Act: -0.0001

Data Index: 121592 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1183. Min Act: -0.0001

Data Index: 291343 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1203. Min Act: -0.0001

Data Index: 329532 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1245. Min Act: -0.0001

Data Index: 53925 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1268. Min Act: -0.0001

Data Index: 392679 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1156. Min Act: -0.0001

Data Index: 960341 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1114. Min Act: -0.0001

Data Index: 149026 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1151. Min Act: -0.0001

Data Index: 249585 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1141151 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1125154 (C4 (Web Text))

Max Activating Token Index: 911