Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4565 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0001

Data Index: 505822 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1153407 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1626524 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1603491 (Python Code)

Max Activating Token Index: 308

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0350. Min Act: -0.0001

Data Index: 938432 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0318. Min Act: -0.0001

Data Index: 97067 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0338. Min Act: -0.0001

Data Index: 549689 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0337. Min Act: -0.0001

Data Index: 173019 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0331. Min Act: -0.0001

Data Index: 973310 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1204763 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0328. Min Act: -0.0001

Data Index: 936374 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1049957 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1522663 (Python Code)

Max Activating Token Index: 857

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0320. Min Act: -0.0001

Data Index: 298831 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0324. Min Act: -0.0001

Data Index: 938630 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1123606 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0330. Min Act: -0.0001

Data Index: 171429 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0311. Min Act: -0.0001

Data Index: 267514 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0307. Min Act: -0.0001

Data Index: 996484 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0300. Min Act: -0.0001

Data Index: 343462 (C4 (Web Text))

Max Activating Token Index: 840