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

Dataset: The Pile

Neuron 360 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: 0.8161. Min Range: -0.8161

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1614847 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1709668 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.7132. Min Act: -0.0000

Data Index: 261603 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6809. Min Act: -0.0000

Data Index: 753393 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1411236 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6353. Min Act: -0.0000

Data Index: 793538 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6210. Min Act: -0.0000

Data Index: 649070 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6566. Min Act: -0.0000

Data Index: 50469 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1048823 (The Pile)

Max Activating Token Index: 804

Text #9

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6084. Min Act: -0.0000

Data Index: 446399 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1342457 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1077259 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1657788 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1670952 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5819. Min Act: -0.0000

Data Index: 343629 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5666. Min Act: -0.0000

Data Index: 205696 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6007. Min Act: -0.0000

Data Index: 600738 (The Pile)

Max Activating Token Index: 1001

Text #17

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5699. Min Act: -0.0000

Data Index: 865611 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6170. Min Act: -0.0000

Data Index: 325200 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1035394 (The Pile)

Max Activating Token Index: 692