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

Dataset: The Pile

Neuron 1442 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5022. Min Act: -0.0000

Data Index: 703134 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5604. Min Act: -0.0000

Data Index: 1158522 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5067. Min Act: -0.0000

Data Index: 298800 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4851. Min Act: -0.0000

Data Index: 272382 (The Pile)

Max Activating Token Index: 994

Text #4

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4819. Min Act: -0.0000

Data Index: 828774 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4756. Min Act: -0.0000

Data Index: 451714 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3875. Min Act: -0.0000

Data Index: 134196 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1623594 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1441067 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1132732 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3478. Min Act: -0.0000

Data Index: 1126913 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1237324 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2956. Min Act: -0.0000

Data Index: 872562 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3606. Min Act: -0.0000

Data Index: 269647 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4399. Min Act: -0.0000

Data Index: 271255 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1603417 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3509. Min Act: -0.0001

Data Index: 1822453 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1720124 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5085. Min Act: -0.0000

Data Index: 1464357 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4181. Min Act: -0.0000

Data Index: 756165 (The Pile)

Max Activating Token Index: 752