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

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

Neuron 105 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1422728 (Python Code)

Max Activating Token Index: 619

Text #1

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1290. Min Act: -0.0001

Data Index: 156830 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1235. Min Act: -0.0001

Data Index: 94408 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1411487 (Python Code)

Max Activating Token Index: 517

Text #4

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1300. Min Act: -0.0001

Data Index: 685097 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1379709 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1121. Min Act: -0.0001

Data Index: 267501 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1256657 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1034882 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1050383 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1187. Min Act: -0.0001

Data Index: 682528 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1159346 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1138. Min Act: -0.0001

Data Index: 512587 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1020. Min Act: -0.0001

Data Index: 677253 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1117726 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1045. Min Act: -0.0001

Data Index: 482272 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1087. Min Act: -0.0001

Data Index: 121935 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0983. Min Act: -0.0001

Data Index: 404571 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1005. Min Act: -0.0001

Data Index: 525082 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1022. Min Act: -0.0001

Data Index: 792701 (C4 (Web Text))

Max Activating Token Index: 506