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

Dataset: The Pile

Neuron 300 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: 1.9602. Min Range: -1.9602

Max Act: 1.9602. Min Act: -0.0000

Data Index: 715139 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.7101. Min Act: -0.0000

Data Index: 1355114 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.5235. Min Act: -0.0000

Data Index: 1681365 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.4547. Min Act: -0.0000

Data Index: 44137 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1427747 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1414 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.3043. Min Act: -0.0000

Data Index: 94597 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.2464. Min Act: -0.0000

Data Index: 1078810 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.2547. Min Act: -0.0001

Data Index: 992095 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.2038. Min Act: -0.0000

Data Index: 886338 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.2094. Min Act: -0.0000

Data Index: 361500 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.1321. Min Act: -0.0000

Data Index: 532616 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1528554 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1979420 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1196485 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1583848 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.1116. Min Act: -0.0000

Data Index: 301350 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.1711. Min Act: -0.0000

Data Index: 1046826 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.1565. Min Act: -0.0000

Data Index: 235450 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 1.9602. Min Range: -1.9602

Max Act: 1.1835. Min Act: -0.0000

Data Index: 1023347 (The Pile)

Max Activating Token Index: 699