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

Dataset: The Pile

Neuron 2449 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: 0.6026. Min Range: -0.6026

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1326965 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1601585 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1810060 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5309. Min Act: -0.0000

Data Index: 206553 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5194. Min Act: -0.0000

Data Index: 207656 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4855. Min Act: -0.0000

Data Index: 596197 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4746. Min Act: -0.0000

Data Index: 848149 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4488. Min Act: -0.0000

Data Index: 771105 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1415207 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1026168 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1524262 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3702. Min Act: -0.0000

Data Index: 930285 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3682. Min Act: -0.0000

Data Index: 835090 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3748. Min Act: -0.0000

Data Index: 399737 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3614. Min Act: -0.0000

Data Index: 508244 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1063665 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3588. Min Act: -0.0000

Data Index: 546347 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3499. Min Act: -0.0000

Data Index: 294950 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3505. Min Act: -0.0000

Data Index: 337274 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1226840 (The Pile)

Max Activating Token Index: 167