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

Dataset: The Pile

Neuron 358 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: 1.6223. Min Range: -1.6223

Max Act: 1.6079. Min Act: -0.0000

Data Index: 1978494 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.4404. Min Act: -0.0000

Data Index: 743361 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.3487. Min Act: -0.0000

Data Index: 252807 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.4515. Min Act: -0.0000

Data Index: 1753421 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.5029. Min Act: -0.0000

Data Index: 962095 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.6223. Min Act: -0.0000

Data Index: 1099091 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2726. Min Act: -0.0000

Data Index: 770240 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1695340 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1927959 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1849465 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9988. Min Act: -0.0000

Data Index: 831747 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.3111. Min Act: -0.0000

Data Index: 1577560 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1624. Min Act: -0.0000

Data Index: 236156 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1028. Min Act: -0.0000

Data Index: 80474 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0750. Min Act: -0.0000

Data Index: 842421 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9841. Min Act: -0.0000

Data Index: 529528 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1011. Min Act: -0.0000

Data Index: 924366 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1642822 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1038090 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0060. Min Act: -0.0000

Data Index: 230457 (The Pile)

Max Activating Token Index: 192