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

Dataset: The Pile

Neuron 3257 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2508. Min Range: -1.2508

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1324466 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 1.2508. Min Range: -1.2508

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1830147 (The Pile)

Max Activating Token Index: 777

Text #2

Max Range: 1.2508. Min Range: -1.2508

Max Act: 1.1206. Min Act: -0.0000

Data Index: 442255 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.9826. Min Act: -0.0000

Data Index: 496065 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 1.2508. Min Range: -1.2508

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1228521 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 1.2508. Min Range: -1.2508

Max Act: 1.0322. Min Act: -0.0000

Data Index: 899358 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1313991 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1735324 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8327. Min Act: -0.0000

Data Index: 67913 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1122621 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1122811 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1339541 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.2508. Min Range: -1.2508

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1932597 (The Pile)

Max Activating Token Index: 359

Text #13

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1695984 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.9059. Min Act: -0.0000

Data Index: 981466 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7195. Min Act: -0.0000

Data Index: 42061 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1256747 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8262. Min Act: -0.0000

Data Index: 535139 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1623972 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1111088 (The Pile)

Max Activating Token Index: 937