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

Dataset: The Pile

Neuron 3571 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1532. Min Range: -1.1532

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1290103 (The Pile)

Max Activating Token Index: 253

Text #1

Max Range: 1.1532. Min Range: -1.1532

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1863053 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 1.1532. Min Range: -1.1532

Max Act: 1.1532. Min Act: -0.0000

Data Index: 500427 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 1.1532. Min Range: -1.1532

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1104998 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 1.1532. Min Range: -1.1532

Max Act: 1.0399. Min Act: -0.0000

Data Index: 928579 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1243486 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9749. Min Act: -0.0000

Data Index: 711741 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1021769 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1524203 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8588. Min Act: -0.0000

Data Index: 511189 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1284406 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8667. Min Act: -0.0000

Data Index: 673219 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9124. Min Act: -0.0000

Data Index: 777269 (The Pile)

Max Activating Token Index: 22

Text #13

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1972027 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8306. Min Act: -0.0000

Data Index: 725106 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1108337 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8011. Min Act: -0.0000

Data Index: 606575 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1915387 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1141785 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.7673. Min Act: -0.0000

Data Index: 607358 (The Pile)

Max Activating Token Index: 872