Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3533 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.4754. Min Act: -0.0001

Data Index: 1283566 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.5476. Min Act: -0.0001

Data Index: 1080788 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.3664. Min Act: -0.0001

Data Index: 436980 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2612. Min Act: -0.0001

Data Index: 1439801 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2541. Min Act: -0.0001

Data Index: 1144028 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2184. Min Act: -0.0001

Data Index: 462441 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2382. Min Act: -0.0001

Data Index: 1553847 (Python Code)

Max Activating Token Index: 135

Text #7

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.0787. Min Act: -0.0001

Data Index: 1506021 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1686. Min Act: -0.0001

Data Index: 1224438 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1916. Min Act: -0.0001

Data Index: 1032346 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1564. Min Act: -0.0001

Data Index: 747561 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2034. Min Act: -0.0001

Data Index: 12733 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1762. Min Act: -0.0001

Data Index: 164160 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1589. Min Act: -0.0001

Data Index: 1075638 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1768. Min Act: -0.0001

Data Index: 359806 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1671. Min Act: -0.0001

Data Index: 590220 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1640. Min Act: -0.0001

Data Index: 773748 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1613. Min Act: -0.0001

Data Index: 1015024 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1301. Min Act: -0.0001

Data Index: 1210092 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1211. Min Act: -0.0001

Data Index: 347905 (C4 (Web Text))

Max Activating Token Index: 380