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

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

Neuron 4582 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0666. Min Range: -1.0666

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1514806 (Python Code)

Max Activating Token Index: 788

Text #1

Max Range: 1.0666. Min Range: -1.0666

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1397045 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 1.0666. Min Range: -1.0666

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1587490 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1399676 (Python Code)

Max Activating Token Index: 18

Text #4

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1500637 (Python Code)

Max Activating Token Index: 990

Text #5

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1654924 (Python Code)

Max Activating Token Index: 456

Text #6

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1653939 (Python Code)

Max Activating Token Index: 756

Text #7

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1440774 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1411687 (Python Code)

Max Activating Token Index: 103

Text #9

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1499049 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1501081 (Python Code)

Max Activating Token Index: 977

Text #11

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1383827 (Python Code)

Max Activating Token Index: 497

Text #12

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1614296 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1373964 (Python Code)

Max Activating Token Index: 485

Text #14

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1379623 (Python Code)

Max Activating Token Index: 296

Text #15

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1485551 (Python Code)

Max Activating Token Index: 720

Text #16

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1636423 (Python Code)

Max Activating Token Index: 922

Text #17

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1401554 (Python Code)

Max Activating Token Index: 754

Text #18

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1449568 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 1.0666. Min Range: -1.0666

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1530477 (Python Code)

Max Activating Token Index: 608