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

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

Neuron 558 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: 0.1538. Min Range: -0.1538

Max Act: 0.1418. Min Act: -0.0001

Data Index: 285687 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0001

Data Index: 807218 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1349. Min Act: -0.0001

Data Index: 180280 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1323. Min Act: -0.0001

Data Index: 69216 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1232. Min Act: -0.0001

Data Index: 771735 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1193. Min Act: -0.0001

Data Index: 524228 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1073792 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1356945 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1126. Min Act: -0.0001

Data Index: 101221 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1235. Min Act: -0.0001

Data Index: 201164 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1199. Min Act: -0.0001

Data Index: 130949 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1332. Min Act: -0.0001

Data Index: 596882 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1091432 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1170290 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1214. Min Act: -0.0001

Data Index: 560590 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1278931 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1150. Min Act: -0.0001

Data Index: 159194 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1145. Min Act: -0.0001

Data Index: 410928 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1128. Min Act: -0.0001

Data Index: 915561 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1210. Min Act: -0.0001

Data Index: 865032 (C4 (Web Text))

Max Activating Token Index: 746