Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 73 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.3082. Min Act: -0.0000

Data Index: 322411 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.1711. Min Act: -0.0000

Data Index: 890280 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.2114. Min Act: -0.0000

Data Index: 341588 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1755590 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1930994 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1733829 (The Pile)

Max Activating Token Index: 986

Text #6

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.1638. Min Act: -0.0000

Data Index: 330755 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0849. Min Act: -0.0000

Data Index: 489155 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1470506 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0768. Min Act: -0.0000

Data Index: 62722 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0513. Min Act: -0.0000

Data Index: 283499 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0398. Min Act: -0.0000

Data Index: 155519 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0453. Min Act: -0.0000

Data Index: 110311 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0256. Min Act: -0.0000

Data Index: 972928 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0801. Min Act: -0.0000

Data Index: 732512 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1671633 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1553736 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1375589 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1289033 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1953347 (The Pile)

Max Activating Token Index: 480