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

Dataset: The Pile

Neuron 3313 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1903772 (The Pile)

Max Activating Token Index: 813

Text #1

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.3029. Min Act: -0.0000

Data Index: 998387 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1034445 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.3009. Min Act: -0.0000

Data Index: 48395 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2896. Min Act: -0.0000

Data Index: 714296 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1992284 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1724329 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2991. Min Act: -0.0000

Data Index: 496209 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1389219 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1548418 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1227295 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1545822 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2660. Min Act: -0.0000

Data Index: 68297 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2286. Min Act: -0.0000

Data Index: 554136 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2064. Min Act: -0.0000

Data Index: 129945 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1727626 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2498. Min Act: -0.0000

Data Index: 937700 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2167. Min Act: -0.0000

Data Index: 685182 (The Pile)

Max Activating Token Index: 803

Text #18

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1455785 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1502300 (The Pile)

Max Activating Token Index: 462