Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 835 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1335. Min Act: -0.0003

Data Index: 1352711 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1223. Min Act: -0.0003

Data Index: 25439 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1181. Min Act: -0.0003

Data Index: 1112864 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1168. Min Act: -0.0003

Data Index: 533578 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1046. Min Act: -0.0003

Data Index: 1649049 (Python Code)

Max Activating Token Index: 802

Text #5

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1059. Min Act: -0.0003

Data Index: 45288 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1053. Min Act: -0.0003

Data Index: 1580659 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1031. Min Act: -0.0003

Data Index: 584678 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1029. Min Act: -0.0003

Data Index: 818899 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1029. Min Act: -0.0003

Data Index: 1407173 (Python Code)

Max Activating Token Index: 380

Text #10

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1016. Min Act: -0.0003

Data Index: 502691 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1026. Min Act: -0.0003

Data Index: 619274 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1028. Min Act: -0.0003

Data Index: 239464 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0994. Min Act: -0.0003

Data Index: 112868 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0991. Min Act: -0.0003

Data Index: 866522 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1516259 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0955. Min Act: -0.0003

Data Index: 1382554 (Python Code)

Max Activating Token Index: 948

Text #17

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1382560 (Python Code)

Max Activating Token Index: 796

Text #18

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1455137 (Python Code)

Max Activating Token Index: 799

Text #19

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0980. Min Act: -0.0003

Data Index: 360677 (C4 (Web Text))

Max Activating Token Index: 238