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

Dataset: The Pile

Neuron 2045 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: 1.4546. Min Range: -1.4546

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1466988 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.4546. Min Act: -0.0000

Data Index: 1815681 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.3551. Min Act: -0.0000

Data Index: 1388009 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.3959. Min Act: -0.0000

Data Index: 670050 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1904533 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.1404. Min Act: -0.0000

Data Index: 555635 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1449718 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0187. Min Act: -0.0000

Data Index: 44687 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1736571 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1942577 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0025. Min Act: -0.0000

Data Index: 33102 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1898439 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1259093 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9411. Min Act: -0.0000

Data Index: 496480 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9700. Min Act: -0.0000

Data Index: 314047 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1341988 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1173663 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1558403 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1760259 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1830669 (The Pile)

Max Activating Token Index: 19