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

Dataset: The Pile

Neuron 3440 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: 3.9691. Min Range: -3.9691

Max Act: 3.9691. Min Act: -0.0000

Data Index: 733894 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.1964. Min Act: -0.0000

Data Index: 1729876 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.9519. Min Act: -0.0000

Data Index: 202195 (The Pile)

Max Activating Token Index: 200

Text #3

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.8870. Min Act: -0.0000

Data Index: 963701 (The Pile)

Max Activating Token Index: 841

Text #4

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.4276. Min Act: -0.0000

Data Index: 946737 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.7081. Min Act: -0.0000

Data Index: 212541 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.6831. Min Act: -0.0000

Data Index: 887226 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.4609. Min Act: -0.0000

Data Index: 886559 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.9403. Min Act: -0.0000

Data Index: 1840482 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.3709. Min Act: -0.0000

Data Index: 106502 (The Pile)

Max Activating Token Index: 407

Text #10

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.1950. Min Act: -0.0000

Data Index: 1464831 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.3110. Min Act: -0.0000

Data Index: 1061676 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.9180. Min Act: -0.0000

Data Index: 594344 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.1466. Min Act: -0.0000

Data Index: 20801 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.1734. Min Act: -0.0000

Data Index: 1645607 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.2989. Min Act: -0.0000

Data Index: 1248479 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.2878. Min Act: -0.0000

Data Index: 261291 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.1364. Min Act: -0.0000

Data Index: 852366 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.2260. Min Act: -0.0000

Data Index: 1043040 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.2380. Min Act: -0.0000

Data Index: 1970106 (The Pile)

Max Activating Token Index: 560