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

Dataset: The Pile

Neuron 5005 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: 0.6313. Min Range: -0.6313

Max Act: 0.6313. Min Act: -0.0000

Data Index: 931205 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1376101 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1236633 (The Pile)

Max Activating Token Index: 192

Text #3

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1790663 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4920. Min Act: -0.0000

Data Index: 3364 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1965967 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1627471 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1068120 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4400. Min Act: -0.0000

Data Index: 243769 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1455792 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1486890 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1186431 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1903025 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3546. Min Act: -0.0000

Data Index: 959564 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4310. Min Act: -0.0000

Data Index: 619239 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4003. Min Act: -0.0000

Data Index: 9825 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1138199 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3661. Min Act: -0.0000

Data Index: 909446 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1155340 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1143200 (The Pile)

Max Activating Token Index: 250