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

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

Neuron 3595 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: 0.1303. Min Range: -0.1303

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1176583 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1298. Min Act: -0.0001

Data Index: 644102 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1255. Min Act: -0.0001

Data Index: 431218 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1194. Min Act: -0.0001

Data Index: 643100 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1290. Min Act: -0.0001

Data Index: 909107 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1280. Min Act: -0.0001

Data Index: 435750 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1032078 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1017220 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1299314 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1167. Min Act: -0.0001

Data Index: 713504 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1162. Min Act: -0.0001

Data Index: 833061 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1151. Min Act: -0.0001

Data Index: 860587 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1256284 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1224. Min Act: -0.0001

Data Index: 981553 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1158. Min Act: -0.0001

Data Index: 480492 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1135. Min Act: -0.0001

Data Index: 618322 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1316994 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1321746 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1022275 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1156. Min Act: -0.0001

Data Index: 425177 (C4 (Web Text))

Max Activating Token Index: 599