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

Dataset: The Pile

Neuron 3116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2946. Min Act: -0.0000

Data Index: 489925 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.9309. Min Act: -0.0000

Data Index: 756863 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.5892. Min Act: -0.0000

Data Index: 691460 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.6643. Min Act: -0.0000

Data Index: 1169046 (The Pile)

Max Activating Token Index: 658

Text #4

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.4806. Min Act: -0.0000

Data Index: 1721541 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.2831. Min Act: -0.0000

Data Index: 691890 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.1264. Min Act: -0.0000

Data Index: 604198 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.4726. Min Act: -0.0000

Data Index: 699836 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.0957. Min Act: -0.0000

Data Index: 1471117 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1912982 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.4415. Min Act: -0.0000

Data Index: 1131333 (The Pile)

Max Activating Token Index: 390

Text #11

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.2891. Min Act: -0.0000

Data Index: 1201634 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.4080. Min Act: -0.0000

Data Index: 1743022 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.1613. Min Act: -0.0000

Data Index: 1051567 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.4171. Min Act: -0.0000

Data Index: 1824347 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.3638. Min Act: -0.0000

Data Index: 697325 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.3655. Min Act: -0.0000

Data Index: 506117 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.2481. Min Act: -0.0000

Data Index: 735901 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 3.2946. Min Range: -3.2946

Max Act: 1.8633. Min Act: -0.0000

Data Index: 139008 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 3.2946. Min Range: -3.2946

Max Act: 2.3218. Min Act: -0.0000

Data Index: 48985 (The Pile)

Max Activating Token Index: 472