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

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

Neuron 2762 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: 0.9735. Min Range: -0.9735

Max Act: 0.9735. Min Act: -0.0000

Data Index: 656097 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.9055. Min Act: -0.0000

Data Index: 126111 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.9165. Min Act: -0.0000

Data Index: 270734 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8328. Min Act: -0.0000

Data Index: 870925 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8076. Min Act: -0.0000

Data Index: 712345 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7678. Min Act: -0.0000

Data Index: 655661 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7807. Min Act: -0.0000

Data Index: 618974 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7534. Min Act: -0.0000

Data Index: 169427 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7460. Min Act: -0.0000

Data Index: 414083 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7658. Min Act: -0.0000

Data Index: 112656 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7408. Min Act: -0.0000

Data Index: 805785 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1139111 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7777. Min Act: -0.0000

Data Index: 330486 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7757. Min Act: -0.0000

Data Index: 558387 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7513. Min Act: -0.0000

Data Index: 540889 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1182747 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7633. Min Act: -0.0000

Data Index: 503151 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7140. Min Act: -0.0000

Data Index: 885652 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1338720 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.7336. Min Act: -0.0000

Data Index: 28013 (C4 (Web Text))

Max Activating Token Index: 761