Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1632 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1366. Min Act: -0.0003

Data Index: 972823 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1357. Min Act: -0.0003

Data Index: 243219 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1154265 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1131. Min Act: -0.0003

Data Index: 860292 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1193030 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1131. Min Act: -0.0003

Data Index: 867827 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1058. Min Act: -0.0002

Data Index: 952045 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1079. Min Act: -0.0003

Data Index: 1123045 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1129. Min Act: -0.0003

Data Index: 1148984 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1051. Min Act: -0.0003

Data Index: 549067 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1075. Min Act: -0.0003

Data Index: 1125603 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1054184 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1101. Min Act: -0.0002

Data Index: 845535 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1024. Min Act: -0.0003

Data Index: 640166 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1024. Min Act: -0.0003

Data Index: 82614 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1288883 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0953. Min Act: -0.0004

Data Index: 666831 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1043. Min Act: -0.0002

Data Index: 1100621 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1008. Min Act: -0.0003

Data Index: 537930 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0987. Min Act: -0.0002

Data Index: 895615 (C4 (Web Text))

Max Activating Token Index: 605