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

Dataset: The Pile

Neuron 2220 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: 0.9904. Min Range: -0.9904

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1017885 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8788. Min Act: 0.0000

Data Index: 24736 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1963322 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7136. Min Act: -0.0000

Data Index: 761638 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6963. Min Act: -0.0000

Data Index: 635520 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7318. Min Act: -0.0000

Data Index: 259615 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6823. Min Act: -0.0000

Data Index: 252472 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.5731. Min Act: -0.0000

Data Index: 587147 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1180975 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6718. Min Act: -0.0000

Data Index: 546535 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.5992. Min Act: -0.0000

Data Index: 473023 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1659707 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6482. Min Act: -0.0000

Data Index: 495311 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6021. Min Act: -0.0000

Data Index: 714759 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1004294 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6538. Min Act: -0.0000

Data Index: 801740 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1924878 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1053240 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1734196 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1411933 (The Pile)

Max Activating Token Index: 277