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

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

Neuron 1625 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: 0.1335. Min Range: -0.1335

Max Act: 0.1335. Min Act: -0.0005

Data Index: 911055 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1165. Min Act: -0.0005

Data Index: 252986 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1258. Min Act: -0.0005

Data Index: 311761 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1175. Min Act: -0.0005

Data Index: 1023085 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1129. Min Act: -0.0005

Data Index: 84470 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1107. Min Act: -0.0005

Data Index: 197378 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1129. Min Act: -0.0005

Data Index: 1058122 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1132. Min Act: -0.0005

Data Index: 688731 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1063. Min Act: -0.0005

Data Index: 287764 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1147. Min Act: -0.0005

Data Index: 976861 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1061. Min Act: -0.0005

Data Index: 872963 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0967. Min Act: -0.0005

Data Index: 237689 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1068. Min Act: -0.0005

Data Index: 758292 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1116. Min Act: -0.0005

Data Index: 511566 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1025. Min Act: -0.0005

Data Index: 1177590 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1062. Min Act: -0.0005

Data Index: 172561 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0943. Min Act: -0.0005

Data Index: 700658 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0954. Min Act: -0.0005

Data Index: 781159 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1061. Min Act: -0.0005

Data Index: 672295 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1058. Min Act: -0.0005

Data Index: 1291333 (C4 (Web Text))

Max Activating Token Index: 357