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

Dataset: The Pile

Neuron 3647 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: 1.9082. Min Range: -1.9082

Max Act: 1.9082. Min Act: -0.0000

Data Index: 1989820 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7604. Min Act: -0.0000

Data Index: 44725 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.6570. Min Act: -0.0000

Data Index: 406621 (The Pile)

Max Activating Token Index: 518

Text #3

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5950. Min Act: -0.0000

Data Index: 695570 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.6932. Min Act: -0.0000

Data Index: 1763397 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.6674. Min Act: -0.0000

Data Index: 1013729 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5758. Min Act: -0.0000

Data Index: 878229 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.6599. Min Act: -0.0000

Data Index: 1222057 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1346627 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.6474. Min Act: -0.0000

Data Index: 738110 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5276. Min Act: -0.0000

Data Index: 1166448 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1511184 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.4885. Min Act: -0.0000

Data Index: 300826 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5566. Min Act: -0.0000

Data Index: 152940 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5518. Min Act: 0.0000

Data Index: 485423 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.4488. Min Act: -0.0000

Data Index: 125710 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5344. Min Act: -0.0000

Data Index: 371455 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5219. Min Act: -0.0000

Data Index: 1170638 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5241. Min Act: -0.0000

Data Index: 1898808 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.4906. Min Act: -0.0000

Data Index: 1158006 (The Pile)

Max Activating Token Index: 659