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

Dataset: The Pile

Neuron 3578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1877. Min Range: -3.1877

Max Act: 3.1877. Min Act: -0.0000

Data Index: 106164 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.8215. Min Act: -0.0000

Data Index: 990891 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.5288. Min Act: -0.0000

Data Index: 816695 (The Pile)

Max Activating Token Index: 895

Text #3

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.0450. Min Act: -0.0000

Data Index: 828109 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.4039. Min Act: -0.0000

Data Index: 1594117 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.1790. Min Act: -0.0000

Data Index: 1581975 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.5016. Min Act: -0.0000

Data Index: 1574211 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.3045. Min Act: -0.0000

Data Index: 1904377 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.2492. Min Act: -0.0000

Data Index: 1422652 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.5113. Min Act: -0.0000

Data Index: 1970199 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.4207. Min Act: -0.0000

Data Index: 1146832 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.5451. Min Act: -0.0000

Data Index: 1957617 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.5492. Min Act: -0.0000

Data Index: 289045 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.3397. Min Act: -0.0000

Data Index: 305418 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.1900. Min Act: -0.0000

Data Index: 717053 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.4099. Min Act: -0.0000

Data Index: 1207645 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 3.1877. Min Range: -3.1877

Max Act: 1.9823. Min Act: -0.0000

Data Index: 969154 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.4970. Min Act: -0.0000

Data Index: 1681835 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.2942. Min Act: -0.0000

Data Index: 1515285 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 3.1877. Min Range: -3.1877

Max Act: 2.1905. Min Act: -0.0000

Data Index: 1353689 (The Pile)

Max Activating Token Index: 1015