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

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

Neuron 1233 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7364. Min Range: -5.7364

Max Act: 5.6515. Min Act: -0.0000

Data Index: 1052070 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 5.7364. Min Range: -5.7364

Max Act: 5.1137. Min Act: -0.0000

Data Index: 268758 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 5.7364. Min Range: -5.7364

Max Act: 5.7364. Min Act: -0.0000

Data Index: 329328 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.9528. Min Act: -0.0000

Data Index: 418703 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.7190. Min Act: -0.0000

Data Index: 792284 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.4922. Min Act: -0.0000

Data Index: 411044 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.8263. Min Act: -0.0000

Data Index: 1344200 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.5982. Min Act: -0.0000

Data Index: 33070 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.9104. Min Act: -0.0000

Data Index: 582910 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.5268. Min Act: -0.0000

Data Index: 61352 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.8687. Min Act: -0.0000

Data Index: 73771 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 5.7364. Min Range: -5.7364

Max Act: 5.0163. Min Act: -0.0000

Data Index: 645206 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.5930. Min Act: -0.0000

Data Index: 1152155 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.6139. Min Act: -0.0000

Data Index: 467214 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.4318. Min Act: -0.0000

Data Index: 780553 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.9436. Min Act: -0.0000

Data Index: 634914 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.6081. Min Act: -0.0000

Data Index: 801178 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.1915. Min Act: -0.0000

Data Index: 998970 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.5614. Min Act: -0.0000

Data Index: 310596 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 5.7364. Min Range: -5.7364

Max Act: 4.3818. Min Act: -0.0000

Data Index: 704234 (C4 (Web Text))

Max Activating Token Index: 678