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

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

Neuron 4877 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1599816 (Python Code)

Max Activating Token Index: 230

Text #1

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.7627. Min Act: -0.0000

Data Index: 442183 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1634569 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1377258 (Python Code)

Max Activating Token Index: 90

Text #4

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.6359. Min Act: -0.0000

Data Index: 312496 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1327061 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.6088. Min Act: -0.0000

Data Index: 469865 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.5634. Min Act: -0.0000

Data Index: 977619 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.6073. Min Act: -0.0000

Data Index: 962748 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.6044. Min Act: -0.0000

Data Index: 749191 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1439246 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.6340. Min Act: -0.0000

Data Index: 150349 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.5768. Min Act: -0.0000

Data Index: 640323 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.5680. Min Act: -0.0000

Data Index: 995012 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.5597. Min Act: -0.0000

Data Index: 812249 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.5786. Min Act: -0.0000

Data Index: 724190 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.5529. Min Act: -0.0000

Data Index: 823888 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1348993 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1388289 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 0.8878. Min Range: -0.8878

Max Act: 0.5157. Min Act: -0.0000

Data Index: 310389 (C4 (Web Text))

Max Activating Token Index: 332