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

Dataset: The Pile

Neuron 2939 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: 5.3966. Min Range: -5.3966

Max Act: 5.3966. Min Act: -0.0000

Data Index: 545654 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.9322. Min Act: -0.0000

Data Index: 867407 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.6334. Min Act: -0.0000

Data Index: 1283331 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.6849. Min Act: -0.0000

Data Index: 353044 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.7680. Min Act: -0.0000

Data Index: 661792 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.6014. Min Act: -0.0000

Data Index: 381663 (The Pile)

Max Activating Token Index: 341

Text #6

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.5360. Min Act: -0.0000

Data Index: 1066606 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.3667. Min Act: -0.0000

Data Index: 310601 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.5034. Min Act: -0.0000

Data Index: 1785918 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.4934. Min Act: -0.0000

Data Index: 799673 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.4635. Min Act: -0.0000

Data Index: 1559018 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.2652. Min Act: -0.0000

Data Index: 1644620 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.2622. Min Act: -0.0000

Data Index: 1550591 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.6070. Min Act: -0.0000

Data Index: 1084426 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.4166. Min Act: -0.0000

Data Index: 1955934 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.3933. Min Act: -0.0000

Data Index: 1992634 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.2072. Min Act: -0.0000

Data Index: 74475 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.3441. Min Act: -0.0000

Data Index: 1700972 (The Pile)

Max Activating Token Index: 803

Text #18

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.3248. Min Act: -0.0000

Data Index: 1526004 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 5.3966. Min Range: -5.3966

Max Act: 4.2673. Min Act: -0.0000

Data Index: 664770 (The Pile)

Max Activating Token Index: 602