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

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

Neuron 188 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6893. Min Act: -0.0000

Data Index: 19937 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6406. Min Act: -0.0000

Data Index: 700881 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1134916 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5293. Min Act: -0.0000

Data Index: 135442 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5127. Min Act: -0.0000

Data Index: 939839 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1017640 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5121. Min Act: -0.0000

Data Index: 195730 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4780. Min Act: -0.0000

Data Index: 44051 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4597. Min Act: -0.0000

Data Index: 244977 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1280072 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4317. Min Act: -0.0000

Data Index: 294975 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4715. Min Act: -0.0000

Data Index: 793530 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4579. Min Act: -0.0000

Data Index: 687362 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4531. Min Act: -0.0000

Data Index: 578304 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1214742 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4649. Min Act: -0.0000

Data Index: 948615 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1438978 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4482. Min Act: -0.0000

Data Index: 207042 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4180. Min Act: -0.0000

Data Index: 966366 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4549. Min Act: -0.0000

Data Index: 87508 (C4 (Web Text))

Max Activating Token Index: 57