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

Dataset: The Pile

Neuron 3169 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: 3.1819. Min Range: -3.1819

Max Act: 2.9237. Min Act: -0.0000

Data Index: 1841026 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1819. Min Act: -0.0000

Data Index: 805363 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.4589. Min Act: -0.0000

Data Index: 1360579 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.4504. Min Act: -0.0000

Data Index: 1719619 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.4242. Min Act: -0.0000

Data Index: 1103685 (The Pile)

Max Activating Token Index: 851

Text #5

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.0284. Min Act: -0.0000

Data Index: 1445127 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.2849. Min Act: -0.0000

Data Index: 923664 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.1239. Min Act: -0.0000

Data Index: 1473784 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.5137. Min Act: -0.0000

Data Index: 386625 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.3332. Min Act: -0.0000

Data Index: 1224333 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.9935. Min Act: -0.0000

Data Index: 1308384 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.9523. Min Act: -0.0000

Data Index: 1524008 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 3.1819. Min Range: -3.1819

Max Act: 2.2156. Min Act: -0.0000

Data Index: 920245 (The Pile)

Max Activating Token Index: 652

Text #13

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.8066. Min Act: -0.0000

Data Index: 1784678 (The Pile)

Max Activating Token Index: 17

Text #14

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.6925. Min Act: -0.0000

Data Index: 878330 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.8219. Min Act: -0.0000

Data Index: 98758 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.8538. Min Act: -0.0000

Data Index: 695526 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.6942. Min Act: -0.0000

Data Index: 1296476 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.6908. Min Act: -0.0000

Data Index: 172483 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 3.1819. Min Range: -3.1819

Max Act: 1.8219. Min Act: -0.0000

Data Index: 489472 (The Pile)

Max Activating Token Index: 225