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

Dataset: The Pile

Neuron 2081 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6908. Min Act: -0.0000

Data Index: 197178 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6675. Min Act: -0.0000

Data Index: 593671 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1952809 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1309854 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1510707 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5125. Min Act: -0.0000

Data Index: 460433 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6546. Min Act: -0.0000

Data Index: 994652 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6214. Min Act: -0.0000

Data Index: 957169 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5526. Min Act: -0.0000

Data Index: 981950 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6112. Min Act: -0.0000

Data Index: 977239 (The Pile)

Max Activating Token Index: 705

Text #10

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1894770 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1890807 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5253. Min Act: -0.0000

Data Index: 743465 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1852702 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1368666 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5529. Min Act: -0.0000

Data Index: 568957 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5388. Min Act: -0.0000

Data Index: 262574 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1514510 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5404. Min Act: -0.0000

Data Index: 836265 (The Pile)

Max Activating Token Index: 872

Text #19

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1293217 (The Pile)

Max Activating Token Index: 265