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

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

Neuron 1924 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.6056. Min Act: -0.0000

Data Index: 1240931 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.2727. Min Act: -0.0000

Data Index: 651066 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.2958. Min Act: -0.0000

Data Index: 949819 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.3303. Min Act: -0.0000

Data Index: 290528 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1214515 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.2188. Min Act: -0.0000

Data Index: 670619 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0920. Min Act: -0.0000

Data Index: 744456 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1318. Min Act: -0.0000

Data Index: 28994 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1040250 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.7531. Min Act: -0.0000

Data Index: 443862 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0512. Min Act: -0.0000

Data Index: 768510 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.2443. Min Act: -0.0000

Data Index: 85350 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.8737. Min Act: -0.0000

Data Index: 553583 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1208959 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.9788. Min Act: -0.0000

Data Index: 155146 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.9156. Min Act: -0.0000

Data Index: 975910 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.8650. Min Act: -0.0000

Data Index: 820047 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.8869. Min Act: -0.0000

Data Index: 248866 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.8273. Min Act: -0.0000

Data Index: 55841 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.6056. Min Range: -1.6056

Max Act: 0.8504. Min Act: -0.0000

Data Index: 447235 (C4 (Web Text))

Max Activating Token Index: 55