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

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

Neuron 704 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.5960. Min Act: -0.0000

Data Index: 1581197 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.4777. Min Act: -0.0000

Data Index: 1393723 (Python Code)

Max Activating Token Index: 300

Text #2

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.4189. Min Act: -0.0000

Data Index: 1611346 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.3996. Min Act: -0.0000

Data Index: 1482152 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2941. Min Act: -0.0000

Data Index: 263306 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1441130 (Python Code)

Max Activating Token Index: 657

Text #6

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1448528 (Python Code)

Max Activating Token Index: 520

Text #7

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.3476. Min Act: -0.0000

Data Index: 1560715 (Python Code)

Max Activating Token Index: 549

Text #8

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1543926 (Python Code)

Max Activating Token Index: 239

Text #9

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1560788 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2479. Min Act: -0.0000

Data Index: 270433 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1654850 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1468637 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2987. Min Act: -0.0000

Data Index: 235206 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2880. Min Act: -0.0000

Data Index: 1555340 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1546112 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1478855 (Python Code)

Max Activating Token Index: 997

Text #17

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1548974 (Python Code)

Max Activating Token Index: 422

Text #18

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1597417 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1482957 (Python Code)

Max Activating Token Index: 931