Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2937 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1121274 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1557746 (The Pile)

Max Activating Token Index: 549

Text #2

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8841. Min Act: -0.0000

Data Index: 247019 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9220. Min Act: -0.0000

Data Index: 409224 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1868127 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8699. Min Act: -0.0000

Data Index: 633592 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1865385 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8173. Min Act: -0.0000

Data Index: 321757 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7772. Min Act: -0.0000

Data Index: 684086 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1082876 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7719. Min Act: -0.0000

Data Index: 695796 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1672565 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8135. Min Act: -0.0000

Data Index: 218739 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1848025 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7640. Min Act: -0.0000

Data Index: 230375 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7360. Min Act: -0.0000

Data Index: 160419 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8031. Min Act: -0.0000

Data Index: 394219 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1793269 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7203. Min Act: 0.0000

Data Index: 1116178 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1408354 (The Pile)

Max Activating Token Index: 1010