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

Dataset: The Pile

Neuron 5057 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1850732 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1143567 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9747. Min Act: -0.0000

Data Index: 669685 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8540. Min Act: -0.0000

Data Index: 149311 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1642181 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8884. Min Act: -0.0000

Data Index: 329479 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8624. Min Act: -0.0000

Data Index: 142620 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9036. Min Act: -0.0000

Data Index: 865418 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9905. Min Act: -0.0000

Data Index: 162724 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7574. Min Act: -0.0000

Data Index: 142685 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9321. Min Act: -0.0000

Data Index: 194098 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1318455 (The Pile)

Max Activating Token Index: 728

Text #12

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9396. Min Act: -0.0000

Data Index: 259056 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1814634 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1447444 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 1.0551. Min Range: -1.0551

Max Act: 1.0551. Min Act: 0.0000

Data Index: 1198727 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9858. Min Act: -0.0000

Data Index: 193700 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9402. Min Act: -0.0000

Data Index: 459989 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1444289 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1340826 (The Pile)

Max Activating Token Index: 422