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

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

Neuron 3493 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.2917. Min Act: -0.0002

Data Index: 468973 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.2837. Min Act: -0.0002

Data Index: 1280662 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.1281. Min Act: -0.0001

Data Index: 537479 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.1746. Min Act: -0.0001

Data Index: 308073 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.1474. Min Act: -0.0001

Data Index: 1437196 (Python Code)

Max Activating Token Index: 760

Text #5

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.0977. Min Act: -0.0001

Data Index: 1487712 (Python Code)

Max Activating Token Index: 257

Text #6

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.1211. Min Act: -0.0001

Data Index: 496022 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.0120. Min Act: -0.0001

Data Index: 957714 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.0459. Min Act: -0.0001

Data Index: 448712 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9762. Min Act: -0.0002

Data Index: 732148 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9626. Min Act: -0.0002

Data Index: 1326015 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.0258. Min Act: -0.0002

Data Index: 413401 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9759. Min Act: -0.0001

Data Index: 566083 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.2917. Min Range: -1.2917

Max Act: 1.0021. Min Act: -0.0001

Data Index: 1222761 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9540. Min Act: -0.0001

Data Index: 598769 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9520. Min Act: -0.0002

Data Index: 548422 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9588. Min Act: -0.0001

Data Index: 223866 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9395. Min Act: -0.0001

Data Index: 1282823 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9917. Min Act: -0.0001

Data Index: 1340665 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.2917. Min Range: -1.2917

Max Act: 0.9329. Min Act: -0.0002

Data Index: 162503 (C4 (Web Text))

Max Activating Token Index: 700