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

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

Neuron 5781 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: 6.6364. Min Range: -6.6364

Max Act: 6.6364. Min Act: -0.0000

Data Index: 1285362 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 6.6364. Min Range: -6.6364

Max Act: 5.0875. Min Act: -0.0000

Data Index: 1226833 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.8652. Min Act: -0.0000

Data Index: 901773 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.8752. Min Act: -0.0000

Data Index: 227556 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.9528. Min Act: -0.0000

Data Index: 367694 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.7084. Min Act: -0.0000

Data Index: 151913 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.6690. Min Act: -0.0000

Data Index: 359103 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.6322. Min Act: -0.0000

Data Index: 200204 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.5395. Min Act: -0.0000

Data Index: 941448 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.6793. Min Act: -0.0000

Data Index: 165818 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.6108. Min Act: -0.0000

Data Index: 441362 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.1475. Min Act: -0.0000

Data Index: 1095054 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.3016. Min Act: -0.0000

Data Index: 69118 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.2836. Min Act: -0.0000

Data Index: 603762 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.0840. Min Act: -0.0000

Data Index: 1006342 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.4222. Min Act: -0.0000

Data Index: 1202361 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.3855. Min Act: -0.0000

Data Index: 287860 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.1858. Min Act: -0.0000

Data Index: 830049 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 6.6364. Min Range: -6.6364

Max Act: 3.9780. Min Act: -0.0000

Data Index: 278587 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 6.6364. Min Range: -6.6364

Max Act: 4.1374. Min Act: -0.0000

Data Index: 419260 (C4 (Web Text))

Max Activating Token Index: 951