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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4111 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8888. Min Act: -0.0000

Data Index: 347377 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1196789 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7499. Min Act: -0.0000

Data Index: 45992 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7603. Min Act: -0.0000

Data Index: 119623 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1302214 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1184742 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8165. Min Act: -0.0000

Data Index: 931975 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8049. Min Act: -0.0000

Data Index: 777964 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7122. Min Act: -0.0000

Data Index: 689956 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8348. Min Act: -0.0000

Data Index: 9443 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8784. Min Act: -0.0000

Data Index: 518056 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7715. Min Act: -0.0000

Data Index: 865951 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8372. Min Act: -0.0000

Data Index: 365722 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8139. Min Act: -0.0000

Data Index: 635808 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6940. Min Act: -0.0000

Data Index: 275298 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7113. Min Act: -0.0000

Data Index: 487027 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1167988 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8107. Min Act: -0.0000

Data Index: 503356 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1259180 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1029495 (C4 (Web Text))

Max Activating Token Index: 892