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

Dataset: The Pile

Neuron 2456 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9991. Min Act: -0.0000

Data Index: 619845 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9327. Min Act: -0.0000

Data Index: 896837 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1765777 (The Pile)

Max Activating Token Index: 222

Text #3

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1827019 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1433314 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9933. Min Act: -0.0000

Data Index: 399225 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8347. Min Act: -0.0000

Data Index: 683069 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1121568 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1003756 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9410. Min Act: -0.0000

Data Index: 871478 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1412300 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1874145 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1388284 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1994959 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0924. Min Act: -0.0000

Data Index: 906509 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1938286 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1582551 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1356710 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1692574 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9712. Min Act: -0.0000

Data Index: 137119 (The Pile)

Max Activating Token Index: 941