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

Dataset: The Pile

Neuron 1356 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6767. Min Act: -0.0000

Data Index: 903399 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1556574 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4277. Min Act: -0.0000

Data Index: 275025 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.3401. Min Act: -0.0000

Data Index: 321112 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1120079 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.3022. Min Act: 0.0000

Data Index: 176794 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1106508 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1388772 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1991116 (The Pile)

Max Activating Token Index: 773

Text #9

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.1669. Min Act: -0.0000

Data Index: 686899 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.1373. Min Act: -0.0000

Data Index: 225687 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1165478 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.1220. Min Act: -0.0000

Data Index: 352357 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1066715 (The Pile)

Max Activating Token Index: 830

Text #14

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.0802. Min Act: -0.0000

Data Index: 929740 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.0709. Min Act: -0.0000

Data Index: 26041 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1509850 (The Pile)

Max Activating Token Index: 23

Text #17

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1710197 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 1.6767. Min Range: -1.6767

Max Act: 0.9704. Min Act: -0.0000

Data Index: 458546 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.0190. Min Act: -0.0000

Data Index: 618801 (The Pile)

Max Activating Token Index: 956