Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2960 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.9908. Min Act: -0.0000

Data Index: 39168 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.7669. Min Act: -0.0000

Data Index: 1690751 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 10.3062. Min Range: -10.3062

Max Act: 10.1453. Min Act: -0.0000

Data Index: 1266008 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.9922. Min Act: -0.0000

Data Index: 1641897 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 10.3062. Min Range: -10.3062

Max Act: 10.2455. Min Act: -0.0000

Data Index: 1840739 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.8466. Min Act: -0.0000

Data Index: 383264 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 10.3062. Min Range: -10.3062

Max Act: 10.3062. Min Act: -0.0000

Data Index: 1537256 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 10.3062. Min Range: -10.3062

Max Act: 10.2585. Min Act: -0.0000

Data Index: 517521 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.9771. Min Act: -0.0000

Data Index: 687136 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.7097. Min Act: -0.0000

Data Index: 1476250 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.6413. Min Act: -0.0000

Data Index: 731823 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.9852. Min Act: -0.0000

Data Index: 63870 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.8231. Min Act: -0.0000

Data Index: 1722858 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 10.3062. Min Range: -10.3062

Max Act: 10.1968. Min Act: -0.0000

Data Index: 184163 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.3428. Min Act: -0.0000

Data Index: 373460 (The Pile)

Max Activating Token Index: 738

Text #15

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.5359. Min Act: -0.0000

Data Index: 12006 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.7991. Min Act: -0.0000

Data Index: 1573736 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.2284. Min Act: -0.0000

Data Index: 1490093 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 10.3062. Min Range: -10.3062

Max Act: 9.4888. Min Act: -0.0000

Data Index: 714742 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 10.3062. Min Range: -10.3062

Max Act: 10.1076. Min Act: -0.0000

Data Index: 1058973 (The Pile)

Max Activating Token Index: 656