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

Dataset: The Pile

Neuron 2052 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: 1.9192. Min Range: -1.9192

Max Act: 1.9192. Min Act: -0.0000

Data Index: 48869 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.4714. Min Act: -0.0000

Data Index: 431695 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.3174. Min Act: -0.0000

Data Index: 1421668 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.3185. Min Act: -0.0000

Data Index: 118114 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1482285 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.0944. Min Act: -0.0000

Data Index: 648114 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1939. Min Act: -0.0000

Data Index: 201416 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.2375. Min Act: -0.0000

Data Index: 877622 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1718. Min Act: -0.0000

Data Index: 217382 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.0529. Min Act: -0.0000

Data Index: 439368 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1838862 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1720. Min Act: -0.0000

Data Index: 1559304 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1400320 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1108498 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1099. Min Act: -0.0000

Data Index: 725508 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1338. Min Act: -0.0000

Data Index: 499117 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1427966 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 1.9192. Min Range: -1.9192

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1841919 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1031934 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1000016 (The Pile)

Max Activating Token Index: 762