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

Dataset: The Pile

Neuron 3767 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9183. Min Range: -3.9183

Max Act: 3.9183. Min Act: -0.0000

Data Index: 1394855 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.7503. Min Act: -0.0000

Data Index: 55279 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.6632. Min Act: -0.0000

Data Index: 209828 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.6477. Min Act: -0.0000

Data Index: 1042390 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.5356. Min Act: -0.0000

Data Index: 945148 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.6426. Min Act: -0.0000

Data Index: 989876 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.3722. Min Act: -0.0000

Data Index: 1322163 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.8148. Min Act: -0.0000

Data Index: 1399736 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.3798. Min Act: -0.0000

Data Index: 44539 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.4965. Min Act: -0.0000

Data Index: 510585 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.3205. Min Act: -0.0000

Data Index: 240208 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.5043. Min Act: -0.0000

Data Index: 1511662 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.2540. Min Act: -0.0000

Data Index: 948997 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.0096. Min Act: -0.0000

Data Index: 786307 (The Pile)

Max Activating Token Index: 547

Text #14

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.1895. Min Act: -0.0000

Data Index: 797973 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.2596. Min Act: -0.0000

Data Index: 946433 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.1069. Min Act: -0.0000

Data Index: 175932 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.1611. Min Act: -0.0000

Data Index: 535110 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 3.9183. Min Range: -3.9183

Max Act: 2.2571. Min Act: -0.0000

Data Index: 777516 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 3.9183. Min Range: -3.9183

Max Act: 1.9945. Min Act: -0.0000

Data Index: 206399 (The Pile)

Max Activating Token Index: 78