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

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

Neuron 2016 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: 0.5004. Min Range: -0.5004

Max Act: 0.5004. Min Act: -0.0000

Data Index: 503498 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4820. Min Act: -0.0000

Data Index: 643727 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4774. Min Act: -0.0000

Data Index: 164865 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4672. Min Act: -0.0000

Data Index: 578811 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4355. Min Act: -0.0000

Data Index: 844476 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4461. Min Act: -0.0000

Data Index: 679733 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1104353 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1243074 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4267. Min Act: -0.0000

Data Index: 865885 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4624. Min Act: -0.0000

Data Index: 360293 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4408. Min Act: -0.0000

Data Index: 721578 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1227233 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4471. Min Act: -0.0000

Data Index: 942660 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4303. Min Act: -0.0000

Data Index: 662288 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3927. Min Act: -0.0000

Data Index: 565241 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4276. Min Act: -0.0000

Data Index: 614251 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4410. Min Act: -0.0000

Data Index: 694815 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1069098 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4262. Min Act: -0.0000

Data Index: 409570 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4477. Min Act: -0.0000

Data Index: 349964 (C4 (Web Text))

Max Activating Token Index: 250