Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1023 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1335. Min Act: -0.0005

Data Index: 1502922 (Python Code)

Max Activating Token Index: 948

Text #1

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1332. Min Act: -0.0005

Data Index: 359169 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1245. Min Act: -0.0005

Data Index: 1544730 (Python Code)

Max Activating Token Index: 296

Text #3

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1185. Min Act: -0.0005

Data Index: 931270 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1372. Min Act: -0.0005

Data Index: 423337 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1202. Min Act: -0.0005

Data Index: 1137623 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1078. Min Act: -0.0005

Data Index: 58337 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1162. Min Act: -0.0005

Data Index: 138713 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1170. Min Act: -0.0005

Data Index: 1348417 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1087. Min Act: -0.0005

Data Index: 872811 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1142. Min Act: -0.0005

Data Index: 70647 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1094. Min Act: -0.0005

Data Index: 1158215 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1137. Min Act: -0.0005

Data Index: 1380665 (Python Code)

Max Activating Token Index: 729

Text #13

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1145. Min Act: -0.0005

Data Index: 628167 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1161. Min Act: -0.0005

Data Index: 384415 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1096. Min Act: -0.0005

Data Index: 28464 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1067. Min Act: -0.0005

Data Index: 592698 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1106. Min Act: -0.0005

Data Index: 1058839 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1157. Min Act: -0.0005

Data Index: 1010268 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1051. Min Act: -0.0005

Data Index: 228245 (C4 (Web Text))

Max Activating Token Index: 790