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

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

Neuron 3047 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1493. Min Act: -0.0003

Data Index: 38422 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1392. Min Act: -0.0002

Data Index: 510522 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1219. Min Act: -0.0003

Data Index: 98521 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1203. Min Act: -0.0002

Data Index: 477065 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1186. Min Act: -0.0003

Data Index: 867291 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1191. Min Act: -0.0003

Data Index: 263514 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1172. Min Act: -0.0002

Data Index: 541425 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1163. Min Act: -0.0002

Data Index: 802976 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1118. Min Act: -0.0003

Data Index: 901125 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1137. Min Act: -0.0002

Data Index: 684576 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1276561 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1126. Min Act: -0.0002

Data Index: 217310 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1102. Min Act: -0.0002

Data Index: 728960 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1108. Min Act: -0.0003

Data Index: 928014 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1148. Min Act: -0.0003

Data Index: 611280 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1025871 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1091. Min Act: -0.0003

Data Index: 629653 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1083. Min Act: -0.0003

Data Index: 291518 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1344366 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1031464 (C4 (Web Text))

Max Activating Token Index: 225