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

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

Neuron 1310 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: 1.9962. Min Range: -1.9962

Max Act: 1.9962. Min Act: -0.0002

Data Index: 177009 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.6482. Min Act: -0.0001

Data Index: 717404 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.4905. Min Act: -0.0002

Data Index: 950656 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.4961. Min Act: -0.0001

Data Index: 1174671 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5187. Min Act: -0.0001

Data Index: 1112212 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.3757. Min Act: -0.0001

Data Index: 665403 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.4527. Min Act: -0.0001

Data Index: 1103786 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.4425. Min Act: -0.0002

Data Index: 1287470 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.3820. Min Act: -0.0002

Data Index: 226507 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.1986. Min Act: -0.0002

Data Index: 1293200 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.2823. Min Act: -0.0002

Data Index: 199225 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.2224. Min Act: -0.0002

Data Index: 444114 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.2493. Min Act: -0.0002

Data Index: 373656 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.2544. Min Act: -0.0002

Data Index: 820399 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.1821. Min Act: -0.0002

Data Index: 906546 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.2488. Min Act: -0.0002

Data Index: 229856 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.1865. Min Act: -0.0001

Data Index: 1110663 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.1717. Min Act: -0.0001

Data Index: 1333690 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.0876. Min Act: -0.0001

Data Index: 321150 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.9962. Min Range: -1.9962

Max Act: 0.9766. Min Act: -0.0002

Data Index: 1333732 (C4 (Web Text))

Max Activating Token Index: 674