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

Dataset: The Pile

Neuron 2292 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: 1.0170. Min Range: -1.0170

Max Act: 1.0170. Min Act: -0.0000

Data Index: 906056 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.9602. Min Act: -0.0000

Data Index: 946867 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.9498. Min Act: -0.0000

Data Index: 267903 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1877058 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1726866 (The Pile)

Max Activating Token Index: 600

Text #5

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1025996 (The Pile)

Max Activating Token Index: 9

Text #6

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8594. Min Act: -0.0000

Data Index: 545676 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1430427 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1794390 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1849484 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1492711 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1390726 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1647224 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7708. Min Act: -0.0000

Data Index: 710287 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7311. Min Act: -0.0000

Data Index: 853730 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1716549 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7339. Min Act: -0.0000

Data Index: 414328 (The Pile)

Max Activating Token Index: 476

Text #17

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1774518 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1138720 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8130. Min Act: -0.0000

Data Index: 80488 (The Pile)

Max Activating Token Index: 354