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

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

Neuron 326 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.4860. Min Act: -0.0001

Data Index: 1654613 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.4956. Min Act: -0.0001

Data Index: 1484595 (Python Code)

Max Activating Token Index: 857

Text #2

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.6176. Min Act: -0.0001

Data Index: 1545226 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5999. Min Act: -0.0001

Data Index: 1420421 (Python Code)

Max Activating Token Index: 988

Text #4

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5349. Min Act: -0.0001

Data Index: 1546229 (Python Code)

Max Activating Token Index: 955

Text #5

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5806. Min Act: -0.0001

Data Index: 1486466 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5679. Min Act: -0.0000

Data Index: 1491828 (Python Code)

Max Activating Token Index: 228

Text #7

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5351. Min Act: -0.0000

Data Index: 1491381 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5785. Min Act: -0.0000

Data Index: 1475069 (Python Code)

Max Activating Token Index: 59

Text #9

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.4709. Min Act: -0.0001

Data Index: 1506882 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5159. Min Act: -0.0001

Data Index: 1617533 (Python Code)

Max Activating Token Index: 534

Text #11

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5657. Min Act: -0.0001

Data Index: 1540010 (Python Code)

Max Activating Token Index: 964

Text #12

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1486358 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5228. Min Act: -0.0001

Data Index: 1623862 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.4610. Min Act: -0.0001

Data Index: 1528549 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.6032. Min Act: -0.0001

Data Index: 1442484 (Python Code)

Max Activating Token Index: 908

Text #16

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5161. Min Act: -0.0001

Data Index: 1490760 (Python Code)

Max Activating Token Index: 967

Text #17

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5519. Min Act: -0.0001

Data Index: 1653338 (Python Code)

Max Activating Token Index: 915

Text #18

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.4399. Min Act: -0.0001

Data Index: 1514470 (Python Code)

Max Activating Token Index: 327

Text #19

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5487. Min Act: -0.0001

Data Index: 1466929 (Python Code)

Max Activating Token Index: 847