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

Dataset: The Pile

Neuron 4855 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1377363 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.0871. Min Act: -0.0000

Data Index: 683773 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9888. Min Act: -0.0000

Data Index: 109556 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1506530 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1736750 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9921. Min Act: -0.0000

Data Index: 29136 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1123363 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1220224 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1695611 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1205426 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9254. Min Act: -0.0000

Data Index: 822414 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1083189 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8960. Min Act: -0.0000

Data Index: 739209 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1031739 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1924957 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1080821 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8849. Min Act: -0.0000

Data Index: 684871 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.7826. Min Act: -0.0000

Data Index: 836125 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8828. Min Act: -0.0000

Data Index: 939607 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9093. Min Act: -0.0000

Data Index: 251082 (The Pile)

Max Activating Token Index: 91