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

Dataset: The Pile

Neuron 84 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: 3.8470. Min Range: -3.8470

Max Act: 3.8470. Min Act: -0.0000

Data Index: 1223729 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.7406. Min Act: -0.0000

Data Index: 355743 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.6095. Min Act: -0.0000

Data Index: 381974 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.2580. Min Act: -0.0000

Data Index: 96860 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.5237. Min Act: -0.0000

Data Index: 1716092 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.5076. Min Act: -0.0000

Data Index: 1266964 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.5249. Min Act: -0.0000

Data Index: 1517380 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.3673. Min Act: -0.0000

Data Index: 831824 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.2067. Min Act: -0.0000

Data Index: 1471178 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.0965. Min Act: -0.0000

Data Index: 256752 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4003. Min Act: -0.0000

Data Index: 406040 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.1355. Min Act: -0.0000

Data Index: 329420 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.0371. Min Act: -0.0000

Data Index: 1712400 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.0804. Min Act: -0.0000

Data Index: 373572 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.3634. Min Act: -0.0000

Data Index: 940048 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.1790. Min Act: -0.0000

Data Index: 1030733 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.9937. Min Act: -0.0000

Data Index: 116601 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.0131. Min Act: -0.0000

Data Index: 1500816 (The Pile)

Max Activating Token Index: 339

Text #18

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4690. Min Act: -0.0000

Data Index: 515334 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.3016. Min Act: -0.0000

Data Index: 237731 (The Pile)

Max Activating Token Index: 93