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

Dataset: The Pile

Neuron 2715 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: 0.4666. Min Range: -0.4666

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1884756 (The Pile)

Max Activating Token Index: 727

Text #1

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1823854 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1289321 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1694937 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3597. Min Act: -0.0000

Data Index: 447032 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3253. Min Act: -0.0000

Data Index: 525525 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1443331 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1335601 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3008. Min Act: -0.0000

Data Index: 979844 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2774. Min Act: -0.0000

Data Index: 947626 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1144681 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1214566 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3070. Min Act: -0.0000

Data Index: 160461 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1505111 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1852056 (The Pile)

Max Activating Token Index: 918

Text #15

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1747027 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1454703 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2635. Min Act: -0.0000

Data Index: 330246 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2486. Min Act: -0.0000

Data Index: 370290 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1112027 (The Pile)

Max Activating Token Index: 798