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

Dataset: The Pile

Neuron 1176 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: 0.9908. Min Range: -0.9908

Max Act: 0.8815. Min Act: -0.0000

Data Index: 890850 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.9040. Min Act: -0.0000

Data Index: 201527 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.9908. Min Act: -0.0000

Data Index: 48999 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1161052 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.9107. Min Act: -0.0000

Data Index: 310499 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8408. Min Act: -0.0000

Data Index: 961669 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7896. Min Act: -0.0000

Data Index: 108376 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1732613 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8491. Min Act: -0.0000

Data Index: 187848 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8617. Min Act: -0.0000

Data Index: 949512 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8853. Min Act: -0.0000

Data Index: 621957 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1035339 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8591. Min Act: -0.0000

Data Index: 605866 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8885. Min Act: -0.0000

Data Index: 862916 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1234683 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1629009 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8663. Min Act: -0.0000

Data Index: 868488 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8623. Min Act: -0.0001

Data Index: 1270639 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1125482 (The Pile)

Max Activating Token Index: 602

Text #19

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1983737 (The Pile)

Max Activating Token Index: 959