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

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

Neuron 762 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6662. Min Range: -4.6662

Max Act: 4.6662. Min Act: -0.0000

Data Index: 881328 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 4.6662. Min Range: -4.6662

Max Act: 4.3473. Min Act: -0.0000

Data Index: 987527 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 4.6662. Min Range: -4.6662

Max Act: 4.2843. Min Act: -0.0000

Data Index: 955306 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 4.6662. Min Range: -4.6662

Max Act: 4.0628. Min Act: -0.0000

Data Index: 231969 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 4.6662. Min Range: -4.6662

Max Act: 4.0397. Min Act: -0.0000

Data Index: 196535 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.6859. Min Act: -0.0000

Data Index: 927615 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.9859. Min Act: -0.0000

Data Index: 174643 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.9324. Min Act: -0.0000

Data Index: 585459 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.6966. Min Act: -0.0000

Data Index: 488770 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.8480. Min Act: -0.0000

Data Index: 1235013 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.7479. Min Act: -0.0000

Data Index: 265933 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.7321. Min Act: -0.0000

Data Index: 640020 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.7220. Min Act: -0.0000

Data Index: 173631 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.5010. Min Act: -0.0000

Data Index: 776868 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.8171. Min Act: -0.0000

Data Index: 1098889 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.4994. Min Act: -0.0000

Data Index: 960297 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.1672. Min Act: -0.0000

Data Index: 537773 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.4154. Min Act: -0.0000

Data Index: 849633 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 4.6662. Min Range: -4.6662

Max Act: 2.7728. Min Act: -0.0000

Data Index: 20250 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 4.6662. Min Range: -4.6662

Max Act: 3.4905. Min Act: -0.0000

Data Index: 1333102 (C4 (Web Text))

Max Activating Token Index: 18