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

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

Neuron 3205 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: 0.6926. Min Range: -0.6926

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1415975 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1641057 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1600615 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1587913 (Python Code)

Max Activating Token Index: 411

Text #4

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1372297 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1656548 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1586781 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1473427 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1617477 (Python Code)

Max Activating Token Index: 285

Text #9

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1448494 (Python Code)

Max Activating Token Index: 963

Text #10

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1511182 (Python Code)

Max Activating Token Index: 206

Text #11

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1459763 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1547875 (Python Code)

Max Activating Token Index: 527

Text #13

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1392795 (Python Code)

Max Activating Token Index: 418

Text #14

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1395553 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1503008 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1478177 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1597463 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1608727 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1613379 (Python Code)

Max Activating Token Index: 940