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

Dataset: The Pile

Neuron 189 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: 1.1758. Min Range: -1.1758

Max Act: 1.1758. Min Act: -0.0000

Data Index: 322353 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9935. Min Act: -0.0000

Data Index: 394652 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1219069 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.1733. Min Act: -0.0000

Data Index: 1396080 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1804483 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0569. Min Act: -0.0000

Data Index: 679643 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1229436 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1711077 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0496. Min Act: -0.0000

Data Index: 502437 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9918. Min Act: -0.0000

Data Index: 161879 (The Pile)

Max Activating Token Index: 867

Text #10

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.1161. Min Act: -0.0000

Data Index: 768075 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1819795 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9699. Min Act: -0.0000

Data Index: 18253 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1544488 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1961971 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9788. Min Act: -0.0000

Data Index: 357723 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1176364 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0089. Min Act: -0.0000

Data Index: 276330 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1032207 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1732338 (The Pile)

Max Activating Token Index: 513