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

Dataset: The Pile

Neuron 4331 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.5909. Min Act: -0.0000

Data Index: 507653 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2977. Min Act: -0.0000

Data Index: 467951 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.1737. Min Act: -0.0000

Data Index: 911530 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1988746 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1345129 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1603958 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9272. Min Act: -0.0000

Data Index: 342711 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1667656 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1926459 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9648. Min Act: -0.0000

Data Index: 638316 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1759394 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9151. Min Act: -0.0000

Data Index: 966512 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1927927 (The Pile)

Max Activating Token Index: 774

Text #13

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9311. Min Act: -0.0000

Data Index: 380338 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1157562 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1642780 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8763. Min Act: -0.0000

Data Index: 830588 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1622602 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1092048 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1629387 (The Pile)

Max Activating Token Index: 649