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

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

Neuron 5464 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: 1.5765. Min Range: -1.5765

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1125343 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.4828. Min Act: -0.0000

Data Index: 300257 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.1665. Min Act: -0.0000

Data Index: 686013 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1065475 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.0597. Min Act: -0.0000

Data Index: 620536 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.9003. Min Act: -0.0000

Data Index: 829645 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.8649. Min Act: -0.0000

Data Index: 969953 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.9241. Min Act: -0.0000

Data Index: 425212 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.8447. Min Act: -0.0000

Data Index: 314210 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.8843. Min Act: -0.0000

Data Index: 596500 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7974. Min Act: -0.0000

Data Index: 513518 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7768. Min Act: -0.0000

Data Index: 295598 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7568. Min Act: -0.0000

Data Index: 772797 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7936. Min Act: -0.0000

Data Index: 974677 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7364. Min Act: -0.0000

Data Index: 91760 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7781. Min Act: -0.0000

Data Index: 617277 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7278. Min Act: -0.0000

Data Index: 941866 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7048. Min Act: -0.0000

Data Index: 141600 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7465. Min Act: -0.0000

Data Index: 647129 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.5765. Min Range: -1.5765

Max Act: 0.7037. Min Act: -0.0000

Data Index: 844329 (C4 (Web Text))

Max Activating Token Index: 458