Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2383. Min Range: -1.2383

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1341153 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.2383. Min Range: -1.2383

Max Act: 1.2027. Min Act: -0.0000

Data Index: 36245 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.2383. Min Range: -1.2383

Max Act: 1.1323. Min Act: -0.0000

Data Index: 832582 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.2383. Min Range: -1.2383

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1220806 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.2383. Min Range: -1.2383

Max Act: 1.0482. Min Act: -0.0000

Data Index: 767714 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9274. Min Act: -0.0000

Data Index: 252408 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9418. Min Act: -0.0000

Data Index: 907923 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9403. Min Act: -0.0000

Data Index: 682305 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1042008 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9486. Min Act: -0.0000

Data Index: 920781 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9739. Min Act: -0.0000

Data Index: 165871 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1346545 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.8799. Min Act: -0.0000

Data Index: 503096 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.8511. Min Act: -0.0000

Data Index: 135731 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9104. Min Act: -0.0000

Data Index: 140840 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.8454. Min Act: -0.0000

Data Index: 267564 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.9031. Min Act: -0.0000

Data Index: 70109 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.8673. Min Act: -0.0000

Data Index: 320043 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.7899. Min Act: -0.0000

Data Index: 676431 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.2383. Min Range: -1.2383

Max Act: 0.8575. Min Act: -0.0000

Data Index: 963896 (C4 (Web Text))

Max Activating Token Index: 185