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

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

Neuron 1808 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.9789. Min Act: -0.0000

Data Index: 1031940 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.9673. Min Act: -0.0000

Data Index: 836668 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.9641. Min Act: -0.0000

Data Index: 77259 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8897. Min Act: -0.0000

Data Index: 850982 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.9901. Min Act: -0.0000

Data Index: 85271 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.7901. Min Act: -0.0000

Data Index: 973699 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.6354. Min Act: -0.0000

Data Index: 75321 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.7316. Min Act: -0.0000

Data Index: 1181854 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.7244. Min Act: -0.0000

Data Index: 845563 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.6429. Min Act: -0.0000

Data Index: 1310968 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.6372. Min Act: -0.0000

Data Index: 605975 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.7609. Min Act: -0.0000

Data Index: 628776 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.6144. Min Act: -0.0000

Data Index: 167113 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.6076. Min Act: -0.0000

Data Index: 683286 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.5910. Min Act: -0.0000

Data Index: 1350647 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.5915. Min Act: -0.0000

Data Index: 188390 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.5755. Min Act: -0.0000

Data Index: 1271592 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.5165. Min Act: -0.0000

Data Index: 976557 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.4903. Min Act: -0.0000

Data Index: 1115227 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.4348. Min Act: -0.0000

Data Index: 1613506 (Python Code)

Max Activating Token Index: 19