Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3588 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.2665. Min Act: -0.0000

Data Index: 1573867 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.4119. Min Act: 0.0000

Data Index: 1636671 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.2284. Min Act: -0.0000

Data Index: 1447626 (Python Code)

Max Activating Token Index: 616

Text #3

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.3250. Min Act: -0.0000

Data Index: 1504051 (Python Code)

Max Activating Token Index: 474

Text #4

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.2974. Min Act: -0.0000

Data Index: 1597670 (Python Code)

Max Activating Token Index: 636

Text #5

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.4083. Min Act: -0.0000

Data Index: 1538088 (Python Code)

Max Activating Token Index: 404

Text #6

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.3416. Min Act: 0.0000

Data Index: 1588090 (Python Code)

Max Activating Token Index: 441

Text #7

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.1031. Min Act: -0.0000

Data Index: 1451638 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.2210. Min Act: -0.0000

Data Index: 1543149 (Python Code)

Max Activating Token Index: 732

Text #9

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.2186. Min Act: -0.0000

Data Index: 1398175 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 2.4119. Min Range: -2.4119

Max Act: 1.9615. Min Act: 0.0000

Data Index: 1385021 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.1812. Min Act: 0.0001

Data Index: 1648497 (Python Code)

Max Activating Token Index: 320

Text #12

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.0425. Min Act: 0.0000

Data Index: 1650769 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.2173. Min Act: -0.0000

Data Index: 1586609 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.0005. Min Act: 0.0000

Data Index: 1642519 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 2.4119. Min Range: -2.4119

Max Act: 2.0576. Min Act: -0.0000

Data Index: 1362484 (Python Code)

Max Activating Token Index: 327

Text #16

Max Range: 2.4119. Min Range: -2.4119

Max Act: 1.8051. Min Act: -0.0000

Data Index: 1585402 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 2.4119. Min Range: -2.4119

Max Act: 1.9228. Min Act: -0.0000

Data Index: 1458346 (Python Code)

Max Activating Token Index: 443

Text #18

Max Range: 2.4119. Min Range: -2.4119

Max Act: 1.9872. Min Act: 0.0000

Data Index: 1433881 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 2.4119. Min Range: -2.4119

Max Act: 1.9805. Min Act: -0.0000

Data Index: 1470920 (Python Code)

Max Activating Token Index: 965