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

Dataset: The Pile

Neuron 1759 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1826029 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1604964 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1061425 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1790555 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1673469 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1443303 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6080. Min Act: -0.0000

Data Index: 6378 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1272947 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1438582 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1432673 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5978. Min Act: -0.0000

Data Index: 711833 (The Pile)

Max Activating Token Index: 717

Text #11

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6105. Min Act: -0.0000

Data Index: 684530 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1579810 (The Pile)

Max Activating Token Index: 622

Text #13

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5860. Min Act: -0.0000

Data Index: 431913 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6111. Min Act: -0.0000

Data Index: 41431 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5855. Min Act: -0.0000

Data Index: 740690 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1381358 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5842. Min Act: -0.0000

Data Index: 515758 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1257555 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1313429 (The Pile)

Max Activating Token Index: 156