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

Dataset: The Pile

Neuron 958 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: 0.3750. Min Range: -0.3750

Max Act: 0.3750. Min Act: -0.0000

Data Index: 271460 (The Pile)

Max Activating Token Index: 391

Text #1

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1660535 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3022. Min Act: 0.0000

Data Index: 1186136 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1662064 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3226. Min Act: -0.0000

Data Index: 872793 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1867417 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1606962 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1014622 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1941717 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2802. Min Act: -0.0000

Data Index: 219429 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1318452 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1952813 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2583. Min Act: -0.0000

Data Index: 314667 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2657. Min Act: -0.0000

Data Index: 493977 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1936931 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1629269 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1179466 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1106516 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2595. Min Act: -0.0000

Data Index: 595067 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2478. Min Act: 0.0000

Data Index: 766647 (The Pile)

Max Activating Token Index: 133