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

Dataset: The Pile

Neuron 3429 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1045031 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1421260 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6189. Min Act: -0.0000

Data Index: 568556 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6846. Min Act: -0.0000

Data Index: 339915 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6546. Min Act: -0.0000

Data Index: 900360 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1033211 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6338. Min Act: -0.0000

Data Index: 287384 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6400. Min Act: -0.0000

Data Index: 542684 (The Pile)

Max Activating Token Index: 904

Text #8

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1400873 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5879. Min Act: -0.0000

Data Index: 949788 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1508412 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1957326 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5786. Min Act: -0.0000

Data Index: 939098 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1211167 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1862394 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5000. Min Act: -0.0000

Data Index: 306363 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.4338. Min Act: -0.0000

Data Index: 641661 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1627281 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.4756. Min Act: -0.0000

Data Index: 543719 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1057654 (The Pile)

Max Activating Token Index: 89