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

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

Neuron 1543 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5967. Min Range: -2.5967

Max Act: 2.5967. Min Act: -0.0000

Data Index: 887738 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 2.5967. Min Range: -2.5967

Max Act: 2.2690. Min Act: -0.0000

Data Index: 90547 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 2.5967. Min Range: -2.5967

Max Act: 2.3638. Min Act: -0.0000

Data Index: 33735 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 2.5967. Min Range: -2.5967

Max Act: 2.4323. Min Act: -0.0000

Data Index: 1147584 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 2.5967. Min Range: -2.5967

Max Act: 2.1870. Min Act: -0.0000

Data Index: 807128 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 2.5967. Min Range: -2.5967

Max Act: 2.0488. Min Act: -0.0000

Data Index: 1352097 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.8959. Min Act: -0.0000

Data Index: 1516379 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.9869. Min Act: -0.0000

Data Index: 1612230 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.9528. Min Act: -0.0000

Data Index: 22033 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.7374. Min Act: -0.0000

Data Index: 348121 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.8544. Min Act: -0.0000

Data Index: 885021 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.9214. Min Act: -0.0000

Data Index: 75031 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.7561. Min Act: -0.0000

Data Index: 1076742 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.8222. Min Act: -0.0000

Data Index: 1559320 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.6780. Min Act: -0.0000

Data Index: 436938 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1488223 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.6606. Min Act: -0.0000

Data Index: 169336 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.6364. Min Act: -0.0000

Data Index: 1198569 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.6405. Min Act: -0.0000

Data Index: 1596775 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 2.5967. Min Range: -2.5967

Max Act: 1.6126. Min Act: -0.0000

Data Index: 1031511 (C4 (Web Text))

Max Activating Token Index: 260