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

Dataset: The Pile

Neuron 3810 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: 0.3862. Min Range: -0.3862

Max Act: 0.3681. Min Act: -0.0000

Data Index: 499762 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1699147 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3599. Min Act: -0.0000

Data Index: 297596 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3162. Min Act: -0.0000

Data Index: 528558 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3084. Min Act: -0.0000

Data Index: 969913 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1601137 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1780005 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2868. Min Act: -0.0000

Data Index: 310069 (The Pile)

Max Activating Token Index: 231

Text #8

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1394011 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1866486 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1819660 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2620. Min Act: -0.0000

Data Index: 930490 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2706. Min Act: -0.0000

Data Index: 759954 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2805. Min Act: -0.0000

Data Index: 42133 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2535. Min Act: -0.0000

Data Index: 452013 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2624. Min Act: 0.0000

Data Index: 1121389 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2557. Min Act: 0.0000

Data Index: 1159093 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2477. Min Act: -0.0000

Data Index: 467298 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2602. Min Act: -0.0000

Data Index: 70766 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2570. Min Act: 0.0000

Data Index: 1903720 (The Pile)

Max Activating Token Index: 324