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

Dataset: The Pile

Neuron 3807 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: 0.9011. Min Range: -0.9011

Max Act: 0.9011. Min Act: -0.0000

Data Index: 679774 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1187192 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1910507 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7306. Min Act: -0.0000

Data Index: 522213 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7494. Min Act: -0.0000

Data Index: 110418 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1848074 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1903060 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7386. Min Act: -0.0000

Data Index: 80125 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1893569 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1374217 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6860. Min Act: -0.0000

Data Index: 531798 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6751. Min Act: -0.0000

Data Index: 451403 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6576. Min Act: -0.0000

Data Index: 369693 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6503. Min Act: -0.0000

Data Index: 331326 (The Pile)

Max Activating Token Index: 309

Text #14

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6639. Min Act: -0.0000

Data Index: 139420 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6599. Min Act: -0.0000

Data Index: 834865 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6706. Min Act: -0.0000

Data Index: 998714 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1325302 (The Pile)

Max Activating Token Index: 553

Text #18

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6444. Min Act: -0.0000

Data Index: 275520 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1794574 (The Pile)

Max Activating Token Index: 421