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

Dataset: The Pile

Neuron 3270 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: 1.8342. Min Range: -1.8342

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1048257 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.8342. Min Act: -0.0000

Data Index: 929225 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.5606. Min Act: -0.0000

Data Index: 781958 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.5142. Min Act: -0.0000

Data Index: 236103 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.6204. Min Act: -0.0000

Data Index: 835305 (The Pile)

Max Activating Token Index: 835

Text #5

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.6783. Min Act: -0.0000

Data Index: 743257 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.5026. Min Act: -0.0000

Data Index: 520963 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.6345. Min Act: -0.0000

Data Index: 1430188 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.5648. Min Act: 0.0000

Data Index: 1748692 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.4461. Min Act: -0.0000

Data Index: 1474484 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.4924. Min Act: -0.0000

Data Index: 388208 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.4745. Min Act: -0.0000

Data Index: 736206 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.5418. Min Act: -0.0000

Data Index: 1929553 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.4067. Min Act: 0.0000

Data Index: 235729 (The Pile)

Max Activating Token Index: 635

Text #14

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1642954 (The Pile)

Max Activating Token Index: 788

Text #15

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.2771. Min Act: -0.0000

Data Index: 526269 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.3351. Min Act: -0.0000

Data Index: 696358 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1561812 (The Pile)

Max Activating Token Index: 459

Text #18

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.3273. Min Act: -0.0000

Data Index: 1713493 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.8342. Min Range: -1.8342

Max Act: 1.6002. Min Act: -0.0000

Data Index: 34620 (The Pile)

Max Activating Token Index: 905