Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2695 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1263394 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3178. Min Act: -0.0000

Data Index: 195067 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2778. Min Act: -0.0000

Data Index: 761669 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1029427 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2566. Min Act: -0.0000

Data Index: 621234 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2517. Min Act: -0.0000

Data Index: 549408 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2357. Min Act: -0.0000

Data Index: 638261 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2395. Min Act: -0.0000

Data Index: 23409 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1062588 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2294. Min Act: -0.0000

Data Index: 732615 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2230. Min Act: -0.0000

Data Index: 559180 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2129. Min Act: -0.0000

Data Index: 264622 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2052. Min Act: -0.0000

Data Index: 631862 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1247088 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2045. Min Act: -0.0000

Data Index: 684886 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2083. Min Act: -0.0000

Data Index: 868823 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.1923. Min Act: -0.0000

Data Index: 479294 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1359329 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.1880. Min Act: -0.0000

Data Index: 8938 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.1857. Min Act: -0.0000

Data Index: 334965 (C4 (Web Text))

Max Activating Token Index: 190