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

Dataset: The Pile

Neuron 281 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: 1.1046. Min Range: -1.1046

Max Act: 1.1046. Min Act: -0.0000

Data Index: 290046 (The Pile)

Max Activating Token Index: 569

Text #1

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9926. Min Act: 0.0000

Data Index: 1783190 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8689. Min Act: -0.0000

Data Index: 432890 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8889. Min Act: -0.0000

Data Index: 35653 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8336. Min Act: -0.0000

Data Index: 407665 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9195. Min Act: -0.0000

Data Index: 170744 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1691890 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8537. Min Act: -0.0000

Data Index: 741582 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8547. Min Act: 0.0000

Data Index: 948336 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1905160 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7920. Min Act: 0.0000

Data Index: 80462 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8413. Min Act: -0.0000

Data Index: 779284 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1846606 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8306. Min Act: -0.0000

Data Index: 151146 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1649443 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1403532 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7938. Min Act: 0.0000

Data Index: 771557 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8346. Min Act: -0.0000

Data Index: 899315 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7780. Min Act: -0.0000

Data Index: 758224 (The Pile)

Max Activating Token Index: 960

Text #19

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8071. Min Act: 0.0000

Data Index: 1737775 (The Pile)

Max Activating Token Index: 819