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

Dataset: The Pile

Neuron 3811 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5718. Min Act: -0.0000

Data Index: 880587 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4461. Min Act: -0.0000

Data Index: 355315 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3976. Min Act: -0.0000

Data Index: 457085 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1643381 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3606. Min Act: -0.0000

Data Index: 804396 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2898. Min Act: -0.0000

Data Index: 279221 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3172. Min Act: -0.0000

Data Index: 901427 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1784356 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1886072 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3094. Min Act: -0.0000

Data Index: 623159 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1062528 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2899. Min Act: -0.0000

Data Index: 119476 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2880. Min Act: -0.0000

Data Index: 342814 (The Pile)

Max Activating Token Index: 796

Text #13

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2858. Min Act: -0.0000

Data Index: 880956 (The Pile)

Max Activating Token Index: 437

Text #14

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2748. Min Act: -0.0000

Data Index: 599790 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2628. Min Act: -0.0000

Data Index: 165550 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2702. Min Act: -0.0000

Data Index: 932831 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2609. Min Act: -0.0000

Data Index: 351221 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2930. Min Act: -0.0000

Data Index: 538856 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2830. Min Act: -0.0000

Data Index: 835678 (The Pile)

Max Activating Token Index: 429