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

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

Neuron 373 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.8772. Min Act: -0.0000

Data Index: 266866 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 2.1962. Min Range: -2.1962

Max Act: 2.1642. Min Act: -0.0000

Data Index: 1622093 (Python Code)

Max Activating Token Index: 236

Text #2

Max Range: 2.1962. Min Range: -2.1962

Max Act: 2.1962. Min Act: -0.0000

Data Index: 1412981 (Python Code)

Max Activating Token Index: 277

Text #3

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.7838. Min Act: -0.0000

Data Index: 1388264 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.6852. Min Act: -0.0000

Data Index: 1395403 (Python Code)

Max Activating Token Index: 957

Text #5

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.6104. Min Act: -0.0000

Data Index: 1030609 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.1049. Min Act: -0.0000

Data Index: 448315 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.5278. Min Act: -0.0000

Data Index: 397326 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.4482. Min Act: -0.0000

Data Index: 948672 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.8558. Min Act: -0.0000

Data Index: 1037205 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1058382 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.4412. Min Act: -0.0000

Data Index: 1516823 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1575152 (Python Code)

Max Activating Token Index: 465

Text #13

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.3826. Min Act: -0.0000

Data Index: 173489 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.5782. Min Act: -0.0000

Data Index: 1552040 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.3754. Min Act: -0.0000

Data Index: 1461951 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.2123. Min Act: -0.0000

Data Index: 493283 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.2209. Min Act: -0.0000

Data Index: 1567901 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1387848 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 2.1962. Min Range: -2.1962

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1506233 (Python Code)

Max Activating Token Index: 759