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

Dataset: The Pile

Neuron 2940 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7585. Min Act: -0.0000

Data Index: 93019 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.8253. Min Act: -0.0000

Data Index: 41872 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.8599. Min Act: -0.0000

Data Index: 793866 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6303. Min Act: -0.0000

Data Index: 916995 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6062. Min Act: -0.0000

Data Index: 1334608 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5754. Min Act: -0.0000

Data Index: 599128 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6590. Min Act: -0.0000

Data Index: 1258821 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6462. Min Act: -0.0000

Data Index: 52917 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6641. Min Act: -0.0000

Data Index: 1564713 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5566. Min Act: -0.0000

Data Index: 1239865 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5449. Min Act: -0.0000

Data Index: 947841 (The Pile)

Max Activating Token Index: 616

Text #11

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5438. Min Act: -0.0000

Data Index: 876370 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.4480. Min Act: -0.0000

Data Index: 1405622 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5334. Min Act: -0.0000

Data Index: 900736 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5835. Min Act: -0.0000

Data Index: 1561751 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.4957. Min Act: -0.0000

Data Index: 546672 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1174053 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.4493. Min Act: -0.0000

Data Index: 532204 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5844. Min Act: -0.0000

Data Index: 640735 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1968151 (The Pile)

Max Activating Token Index: 610