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

Dataset: The Pile

Neuron 2048 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5590. Min Act: -0.0000

Data Index: 21253 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5543. Min Act: -0.0000

Data Index: 982352 (The Pile)

Max Activating Token Index: 384

Text #2

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1753522 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5331. Min Act: -0.0000

Data Index: 703354 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5075. Min Act: -0.0000

Data Index: 237069 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4879. Min Act: -0.0000

Data Index: 352926 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4890. Min Act: -0.0000

Data Index: 10632 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1962740 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4808. Min Act: -0.0000

Data Index: 466335 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4776. Min Act: -0.0000

Data Index: 96416 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4927. Min Act: 0.0000

Data Index: 1336596 (The Pile)

Max Activating Token Index: 435

Text #11

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4561. Min Act: -0.0000

Data Index: 885732 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1566608 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1989589 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4907. Min Act: -0.0000

Data Index: 819201 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1945924 (The Pile)

Max Activating Token Index: 366

Text #16

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1400246 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1319858 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1534813 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4746. Min Act: -0.0000

Data Index: 105047 (The Pile)

Max Activating Token Index: 463