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

Dataset: The Pile

Neuron 2821 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.2195. Min Act: 0.0000

Data Index: 1593738 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0734. Min Act: -0.0000

Data Index: 31882 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1261690 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1171426 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1879672 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8913. Min Act: -0.0000

Data Index: 502906 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.9199. Min Act: -0.0000

Data Index: 632926 (The Pile)

Max Activating Token Index: 676

Text #7

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8025. Min Act: 0.0000

Data Index: 531884 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1677440 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8431. Min Act: -0.0000

Data Index: 77280 (The Pile)

Max Activating Token Index: 983

Text #10

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8021. Min Act: 0.0000

Data Index: 1090341 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1483691 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.7848. Min Act: 0.0000

Data Index: 67636 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1154251 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.7785. Min Act: -0.0000

Data Index: 713350 (The Pile)

Max Activating Token Index: 620

Text #15

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1958935 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1461831 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.7545. Min Act: 0.0000

Data Index: 876073 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.7431. Min Act: -0.0000

Data Index: 191446 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.7322. Min Act: 0.0000

Data Index: 1588278 (The Pile)

Max Activating Token Index: 912