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

Dataset: The Pile

Neuron 606 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.8300. Min Act: -0.0000

Data Index: 689367 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1260601 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1722808 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1350110 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1843450 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.8229. Min Act: -0.0000

Data Index: 97056 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1393056 (The Pile)

Max Activating Token Index: 570

Text #7

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1417530 (The Pile)

Max Activating Token Index: 202

Text #8

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1318029 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7113. Min Act: -0.0000

Data Index: 351834 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7390. Min Act: -0.0000

Data Index: 57395 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1188724 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.6888. Min Act: -0.0000

Data Index: 684577 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.6966. Min Act: -0.0000

Data Index: 349529 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.6689. Min Act: -0.0000

Data Index: 195711 (The Pile)

Max Activating Token Index: 310

Text #15

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1688210 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1991490 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.6690. Min Act: -0.0000

Data Index: 500317 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.6921. Min Act: -0.0000

Data Index: 362810 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7308. Min Act: -0.0000

Data Index: 112890 (The Pile)

Max Activating Token Index: 150