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

Dataset: The Pile

Neuron 1549 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: 1.4863. Min Range: -1.4863

Max Act: 1.4863. Min Act: -0.0000

Data Index: 974205 (The Pile)

Max Activating Token Index: 577

Text #1

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1936161 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1237833 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.3138. Min Act: -0.0000

Data Index: 1657900 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1046008 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.2829. Min Act: -0.0000

Data Index: 435208 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1414782 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.2612. Min Act: -0.0000

Data Index: 148917 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.2450. Min Act: -0.0000

Data Index: 438914 (The Pile)

Max Activating Token Index: 842

Text #9

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.0892. Min Act: -0.0000

Data Index: 601546 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.0625. Min Act: -0.0000

Data Index: 254907 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1424718 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.0888. Min Act: -0.0000

Data Index: 895310 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1470241 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1858970 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.0786. Min Act: -0.0000

Data Index: 780593 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1418046 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.1842. Min Act: -0.0000

Data Index: 298284 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.1173. Min Act: -0.0000

Data Index: 396368 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1049649 (The Pile)

Max Activating Token Index: 893