Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2400 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1384. Min Act: -0.0001

Data Index: 527133 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1483. Min Act: -0.0002

Data Index: 918837 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1239873 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1200. Min Act: -0.0001

Data Index: 755493 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1232. Min Act: -0.0001

Data Index: 7597 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1191. Min Act: -0.0001

Data Index: 157831 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1294988 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1132. Min Act: -0.0002

Data Index: 319153 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1060. Min Act: -0.0001

Data Index: 404614 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1032698 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1322510 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1107. Min Act: -0.0002

Data Index: 402404 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1259052 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1051. Min Act: -0.0001

Data Index: 937497 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1058. Min Act: -0.0001

Data Index: 301561 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1317925 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1109. Min Act: -0.0001

Data Index: 746697 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1057. Min Act: -0.0001

Data Index: 404620 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1101. Min Act: -0.0001

Data Index: 710654 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1064. Min Act: -0.0001

Data Index: 848795 (C4 (Web Text))

Max Activating Token Index: 127