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

Dataset: The Pile

Neuron 1894 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8842. Min Act: -0.0000

Data Index: 1902254 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.9862. Min Act: -0.0000

Data Index: 1791847 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8171. Min Act: -0.0000

Data Index: 349007 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7292. Min Act: -0.0000

Data Index: 1111498 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8124. Min Act: -0.0000

Data Index: 602857 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7074. Min Act: -0.0000

Data Index: 714436 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.6697. Min Act: -0.0000

Data Index: 311778 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5480. Min Act: -0.0000

Data Index: 552116 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1800617 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5733. Min Act: -0.0000

Data Index: 876700 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4505. Min Act: -0.0000

Data Index: 95388 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5543. Min Act: -0.0000

Data Index: 1531698 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4631. Min Act: -0.0000

Data Index: 404459 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5014. Min Act: -0.0000

Data Index: 696969 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.3362. Min Act: -0.0000

Data Index: 292667 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5227. Min Act: -0.0000

Data Index: 1795161 (The Pile)

Max Activating Token Index: 120

Text #16

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1920585 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4625. Min Act: -0.0000

Data Index: 523835 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4267. Min Act: -0.0000

Data Index: 838421 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1153696 (The Pile)

Max Activating Token Index: 93