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

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

Neuron 3404 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: 2.7362. Min Range: -2.7362

Max Act: 2.7362. Min Act: -0.0000

Data Index: 56315 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.4350. Min Act: -0.0000

Data Index: 1139883 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.3984. Min Act: -0.0000

Data Index: 1247581 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.2045. Min Act: -0.0000

Data Index: 861876 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0631. Min Act: -0.0000

Data Index: 261581 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.1071. Min Act: -0.0000

Data Index: 357839 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0470. Min Act: -0.0000

Data Index: 870553 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0601. Min Act: -0.0000

Data Index: 36577 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9252. Min Act: -0.0000

Data Index: 58488 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.8793. Min Act: -0.0000

Data Index: 751455 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.1292. Min Act: -0.0000

Data Index: 1249354 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9918. Min Act: -0.0000

Data Index: 1088375 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0846. Min Act: -0.0000

Data Index: 199792 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.2111. Min Act: -0.0000

Data Index: 1125861 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0622. Min Act: -0.0000

Data Index: 238201 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0771. Min Act: -0.0000

Data Index: 1282904 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9611. Min Act: -0.0000

Data Index: 1222177 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9511. Min Act: -0.0000

Data Index: 857909 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0395. Min Act: -0.0000

Data Index: 154426 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0408. Min Act: -0.0000

Data Index: 350804 (C4 (Web Text))

Max Activating Token Index: 528