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

Dataset: The Pile

Neuron 175 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1207134 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1004633 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4709. Min Act: -0.0000

Data Index: 245641 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5208. Min Act: -0.0000

Data Index: 935808 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1694357 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1018144 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1255565 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1683504 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1729989 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3782. Min Act: -0.0000

Data Index: 446145 (The Pile)

Max Activating Token Index: 996

Text #10

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1277207 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1587229 (The Pile)

Max Activating Token Index: 828

Text #12

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1471896 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1712717 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1538736 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.2898. Min Act: -0.0000

Data Index: 417055 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.2846. Min Act: -0.0000

Data Index: 32997 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1797278 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1615446 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.2133. Min Act: -0.0000

Data Index: 490332 (The Pile)

Max Activating Token Index: 761