Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2624 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3963. Min Act: -0.0001

Data Index: 829320 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2610. Min Act: -0.0001

Data Index: 1168924 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2161. Min Act: -0.0001

Data Index: 244755 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2313. Min Act: -0.0001

Data Index: 507338 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2195. Min Act: -0.0001

Data Index: 158602 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1235441 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2112. Min Act: -0.0001

Data Index: 894921 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2047. Min Act: -0.0001

Data Index: 607522 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1903. Min Act: -0.0001

Data Index: 977475 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1936. Min Act: -0.0001

Data Index: 403697 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1987. Min Act: -0.0001

Data Index: 535906 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2028. Min Act: -0.0001

Data Index: 765930 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1817. Min Act: -0.0001

Data Index: 704737 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1884. Min Act: -0.0001

Data Index: 359995 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1830. Min Act: -0.0001

Data Index: 659217 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1902. Min Act: -0.0001

Data Index: 587556 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1856. Min Act: -0.0001

Data Index: 566541 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1881. Min Act: -0.0000

Data Index: 756854 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1839. Min Act: -0.0001

Data Index: 461798 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.1843. Min Act: -0.0001

Data Index: 434398 (C4 (Web Text))

Max Activating Token Index: 379