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

Dataset: The Pile

Neuron 852 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: 0.2665. Min Range: -0.2665

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1906815 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2485. Min Act: -0.0000

Data Index: 403110 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2663. Min Act: 0.0000

Data Index: 1385552 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1118602 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2571. Min Act: -0.0000

Data Index: 786024 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1339652 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2207. Min Act: -0.0000

Data Index: 499114 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1675605 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2050. Min Act: -0.0000

Data Index: 28503 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2257. Min Act: -0.0000

Data Index: 633912 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1963207 (The Pile)

Max Activating Token Index: 513

Text #11

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2139. Min Act: -0.0000

Data Index: 870549 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1763320 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2118. Min Act: 0.0000

Data Index: 946210 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2180. Min Act: -0.0000

Data Index: 725161 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1513815 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2024. Min Act: -0.0000

Data Index: 691939 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1563532 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1866363 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1567050 (The Pile)

Max Activating Token Index: 664