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

Dataset: The Pile

Neuron 4188 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.7472. Min Act: -0.0000

Data Index: 738731 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5545. Min Act: -0.0000

Data Index: 77420 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4556. Min Act: -0.0000

Data Index: 105281 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1654508 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1934669 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1094622 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1404051 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4142. Min Act: -0.0000

Data Index: 496043 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3783. Min Act: -0.0000

Data Index: 383062 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4124. Min Act: -0.0000

Data Index: 272170 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1439362 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1235260 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4108. Min Act: -0.0000

Data Index: 116395 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3974. Min Act: -0.0000

Data Index: 743755 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1432208 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3846. Min Act: -0.0000

Data Index: 507872 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3807. Min Act: -0.0000

Data Index: 800080 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1673258 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.3793. Min Act: -0.0000

Data Index: 772939 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1758956 (The Pile)

Max Activating Token Index: 632