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

Dataset: The Pile

Neuron 653 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: 0.9953. Min Range: -0.9953

Max Act: 0.9953. Min Act: -0.0000

Data Index: 940363 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1011120 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1584771 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1862246 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1298810 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3746. Min Act: -0.0000

Data Index: 974405 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.4309. Min Act: -0.0000

Data Index: 694050 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.4644. Min Act: -0.0000

Data Index: 532259 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1433834 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1467590 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1927101 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1209240 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1385111 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1011276 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3682. Min Act: -0.0000

Data Index: 290233 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3304. Min Act: -0.0000

Data Index: 597440 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3835. Min Act: -0.0000

Data Index: 431787 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1678813 (The Pile)

Max Activating Token Index: 70

Text #18

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.3732. Min Act: -0.0000

Data Index: 481603 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.2588. Min Act: -0.0000

Data Index: 576570 (The Pile)

Max Activating Token Index: 427