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

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

Neuron 84 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1263. Min Act: -0.0003

Data Index: 1338136 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1289. Min Act: -0.0003

Data Index: 1084393 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1204. Min Act: -0.0003

Data Index: 89469 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1225. Min Act: -0.0003

Data Index: 1280038 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1138. Min Act: -0.0003

Data Index: 922296 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1214. Min Act: -0.0003

Data Index: 1014144 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1254. Min Act: -0.0003

Data Index: 398020 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1264. Min Act: -0.0003

Data Index: 733980 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1236. Min Act: -0.0003

Data Index: 971972 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1228. Min Act: -0.0003

Data Index: 1317039 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1135. Min Act: -0.0003

Data Index: 486920 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1192. Min Act: -0.0003

Data Index: 512421 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1266. Min Act: -0.0003

Data Index: 34500 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1174. Min Act: -0.0003

Data Index: 75294 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1170. Min Act: -0.0003

Data Index: 630459 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1160. Min Act: -0.0003

Data Index: 106202 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1200. Min Act: -0.0003

Data Index: 1135813 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1200. Min Act: -0.0003

Data Index: 1172622 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1153. Min Act: -0.0003

Data Index: 193675 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1204. Min Act: -0.0003

Data Index: 283196 (C4 (Web Text))

Max Activating Token Index: 120