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

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

Neuron 381 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: 2.4031. Min Range: -2.4031

Max Act: 2.4031. Min Act: -0.0000

Data Index: 1438499 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 2.4031. Min Range: -2.4031

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1420273 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 2.4031. Min Range: -2.4031

Max Act: 2.1254. Min Act: -0.0000

Data Index: 1491258 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 2.4031. Min Range: -2.4031

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1003367 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 2.4031. Min Range: -2.4031

Max Act: 2.0468. Min Act: -0.0000

Data Index: 1459529 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.9151. Min Act: -0.0000

Data Index: 1646015 (Python Code)

Max Activating Token Index: 826

Text #6

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.9076. Min Act: -0.0000

Data Index: 865925 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 2.4031. Min Range: -2.4031

Max Act: 2.0023. Min Act: -0.0000

Data Index: 1442414 (Python Code)

Max Activating Token Index: 286

Text #8

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.9430. Min Act: -0.0000

Data Index: 1615159 (Python Code)

Max Activating Token Index: 209

Text #9

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.8281. Min Act: -0.0000

Data Index: 1534741 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.9129. Min Act: -0.0000

Data Index: 654730 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.7822. Min Act: -0.0000

Data Index: 823758 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.8982. Min Act: -0.0000

Data Index: 1539776 (Python Code)

Max Activating Token Index: 562

Text #13

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.7791. Min Act: -0.0000

Data Index: 893170 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.8723. Min Act: -0.0000

Data Index: 1518648 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.8558. Min Act: -0.0000

Data Index: 217956 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.7882. Min Act: -0.0000

Data Index: 960791 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1417218 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.8401. Min Act: -0.0000

Data Index: 837187 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 2.4031. Min Range: -2.4031

Max Act: 1.9355. Min Act: -0.0000

Data Index: 345706 (C4 (Web Text))

Max Activating Token Index: 488