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

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

Neuron 5642 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: 1.1963. Min Range: -1.1963

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1280750 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.1685. Min Act: -0.0000

Data Index: 372179 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.1814. Min Act: -0.0000

Data Index: 376377 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1148782 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1218429 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0711. Min Act: -0.0000

Data Index: 384162 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0879. Min Act: -0.0000

Data Index: 103469 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0505. Min Act: -0.0000

Data Index: 510453 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.1062. Min Act: -0.0000

Data Index: 754721 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1286571 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1129284 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0377. Min Act: -0.0000

Data Index: 109049 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0373. Min Act: -0.0000

Data Index: 896459 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9619. Min Act: -0.0000

Data Index: 4796 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9396. Min Act: -0.0000

Data Index: 419076 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0271. Min Act: -0.0000

Data Index: 792779 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1195351 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9793. Min Act: -0.0000

Data Index: 992351 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9396. Min Act: -0.0000

Data Index: 342979 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9813. Min Act: -0.0000

Data Index: 545757 (C4 (Web Text))

Max Activating Token Index: 287