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

Dataset: The Pile

Neuron 3264 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: 3.9357. Min Range: -3.9357

Max Act: 3.9357. Min Act: -0.0000

Data Index: 1720736 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.8924. Min Act: -0.0000

Data Index: 26499 (The Pile)

Max Activating Token Index: 10

Text #2

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.5545. Min Act: -0.0000

Data Index: 152405 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.8351. Min Act: -0.0000

Data Index: 1025774 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.6877. Min Act: -0.0000

Data Index: 1969801 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.4579. Min Act: -0.0000

Data Index: 1123529 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.4812. Min Act: -0.0000

Data Index: 145198 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.7633. Min Act: -0.0000

Data Index: 739947 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.5336. Min Act: -0.0000

Data Index: 1436184 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.3372. Min Act: -0.0000

Data Index: 1941238 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.4616. Min Act: -0.0000

Data Index: 359592 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.3940. Min Act: -0.0000

Data Index: 66633 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.2143. Min Act: -0.0000

Data Index: 1319853 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.2252. Min Act: -0.0000

Data Index: 1257285 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.3875. Min Act: -0.0000

Data Index: 1638618 (The Pile)

Max Activating Token Index: 467

Text #15

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.3493. Min Act: -0.0000

Data Index: 1543556 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.3780. Min Act: -0.0000

Data Index: 116739 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.3521. Min Act: -0.0000

Data Index: 1747293 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.1929. Min Act: -0.0000

Data Index: 1075131 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 3.9357. Min Range: -3.9357

Max Act: 3.1927. Min Act: -0.0000

Data Index: 1873365 (The Pile)

Max Activating Token Index: 234