Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2467 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1286. Min Act: -0.0001

Data Index: 505750 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1214. Min Act: -0.0001

Data Index: 692058 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1271. Min Act: -0.0001

Data Index: 898317 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1297415 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1125. Min Act: -0.0001

Data Index: 785359 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1156. Min Act: -0.0001

Data Index: 731216 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1215. Min Act: -0.0001

Data Index: 909266 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1128. Min Act: -0.0001

Data Index: 123171 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1119. Min Act: -0.0001

Data Index: 198542 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1050020 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1265052 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1237. Min Act: -0.0001

Data Index: 999070 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1152. Min Act: -0.0001

Data Index: 94608 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1242. Min Act: -0.0001

Data Index: 270202 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1161. Min Act: -0.0001

Data Index: 664475 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1157. Min Act: -0.0001

Data Index: 758790 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1192. Min Act: -0.0001

Data Index: 375200 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1005. Min Act: -0.0001

Data Index: 709324 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1190423 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1171. Min Act: -0.0001

Data Index: 768271 (C4 (Web Text))

Max Activating Token Index: 426