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

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

Neuron 2504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5725. Min Act: -0.0001

Data Index: 346905 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5328. Min Act: -0.0001

Data Index: 542840 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4300. Min Act: -0.0001

Data Index: 999420 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4082. Min Act: -0.0001

Data Index: 35140 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4493. Min Act: -0.0001

Data Index: 586820 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4370. Min Act: -0.0001

Data Index: 474042 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4461. Min Act: -0.0001

Data Index: 36948 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4175. Min Act: -0.0001

Data Index: 84483 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4684. Min Act: -0.0001

Data Index: 492725 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4363. Min Act: -0.0001

Data Index: 1338892 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4366. Min Act: -0.0001

Data Index: 831992 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4419. Min Act: -0.0001

Data Index: 953932 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4189. Min Act: -0.0001

Data Index: 1248780 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4155. Min Act: -0.0001

Data Index: 981942 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4226. Min Act: -0.0001

Data Index: 612524 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4335. Min Act: -0.0001

Data Index: 975291 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4268. Min Act: -0.0001

Data Index: 557314 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3503. Min Act: -0.0001

Data Index: 350214 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1229400 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3840. Min Act: -0.0001

Data Index: 184714 (C4 (Web Text))

Max Activating Token Index: 437