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

Dataset: The Pile

Neuron 3264 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2951. Min Act: -0.0000

Data Index: 842812 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2935. Min Act: -0.0000

Data Index: 564143 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1869601 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2080. Min Act: -0.0000

Data Index: 612354 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1943456 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0609. Min Act: -0.0000

Data Index: 551049 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1778931 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0269. Min Act: -0.0000

Data Index: 788893 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1978035 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.9040. Min Act: -0.0000

Data Index: 907252 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1069210 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1387900 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1525356 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.8540. Min Act: -0.0000

Data Index: 758360 (The Pile)

Max Activating Token Index: 697

Text #14

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.7830. Min Act: -0.0000

Data Index: 801006 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1169143 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1541144 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.8983. Min Act: -0.0000

Data Index: 878435 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.8236. Min Act: -0.0000

Data Index: 98567 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.8917. Min Act: -0.0000

Data Index: 267673 (The Pile)

Max Activating Token Index: 885