Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.9095. Min Act: -0.0000

Data Index: 879123 (The Pile)

Max Activating Token Index: 588

Text #1

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.9620. Min Act: -0.0000

Data Index: 640091 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 1.0323. Min Range: -1.0323

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1525605 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1100695 (The Pile)

Max Activating Token Index: 778

Text #4

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.9846. Min Act: -0.0000

Data Index: 980636 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1639685 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.9080. Min Act: -0.0000

Data Index: 773825 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8716. Min Act: -0.0000

Data Index: 167124 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.9158. Min Act: -0.0000

Data Index: 319461 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1736620 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1640910 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1929877 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8320. Min Act: -0.0000

Data Index: 882892 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8563. Min Act: -0.0000

Data Index: 490434 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1665626 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.7980. Min Act: -0.0000

Data Index: 709962 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8167. Min Act: -0.0000

Data Index: 174836 (The Pile)

Max Activating Token Index: 440

Text #17

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1974433 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8393. Min Act: -0.0000

Data Index: 368874 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 1.0323. Min Range: -1.0323

Max Act: 0.8316. Min Act: -0.0000

Data Index: 940403 (The Pile)

Max Activating Token Index: 26