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

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

Neuron 1370 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.7153. Min Act: -0.0000

Data Index: 571447 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.7028. Min Act: -0.0000

Data Index: 833421 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.5181. Min Act: -0.0000

Data Index: 575024 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1313627 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.5523. Min Act: -0.0000

Data Index: 866515 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.2888. Min Act: -0.0000

Data Index: 585142 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.3248. Min Act: -0.0000

Data Index: 911710 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1132038 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.2887. Min Act: -0.0000

Data Index: 790355 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.2506. Min Act: -0.0000

Data Index: 977532 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.1851. Min Act: -0.0000

Data Index: 311990 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.1596. Min Act: -0.0000

Data Index: 94384 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.1807. Min Act: -0.0000

Data Index: 877035 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1157829 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1296449 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.1250. Min Act: -0.0000

Data Index: 644668 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1279703 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1182546 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1294015 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.0488. Min Act: -0.0000

Data Index: 671965 (C4 (Web Text))

Max Activating Token Index: 214