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

Dataset: The Pile

Neuron 2362 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: 3.8612. Min Range: -3.8612

Max Act: 3.8612. Min Act: -0.0000

Data Index: 610904 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 3.8612. Min Range: -3.8612

Max Act: 3.3442. Min Act: -0.0000

Data Index: 1210410 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 3.8612. Min Range: -3.8612

Max Act: 3.4680. Min Act: -0.0000

Data Index: 665539 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 3.8612. Min Range: -3.8612

Max Act: 3.4664. Min Act: -0.0000

Data Index: 1331235 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 3.8612. Min Range: -3.8612

Max Act: 3.2537. Min Act: -0.0000

Data Index: 1042539 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 3.8612. Min Range: -3.8612

Max Act: 3.0207. Min Act: -0.0000

Data Index: 1234427 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 3.8612. Min Range: -3.8612

Max Act: 3.1268. Min Act: -0.0000

Data Index: 1492551 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.8287. Min Act: -0.0000

Data Index: 278559 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 3.8612. Min Range: -3.8612

Max Act: 3.0827. Min Act: -0.0000

Data Index: 1763560 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.8273. Min Act: -0.0000

Data Index: 1616867 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.6760. Min Act: -0.0000

Data Index: 1073469 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.9240. Min Act: -0.0000

Data Index: 1865657 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.7645. Min Act: -0.0000

Data Index: 1916457 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.9037. Min Act: -0.0000

Data Index: 1340635 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.7211. Min Act: -0.0000

Data Index: 940584 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.4898. Min Act: -0.0000

Data Index: 329909 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.6026. Min Act: -0.0000

Data Index: 451463 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.5982. Min Act: -0.0000

Data Index: 49706 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.4364. Min Act: -0.0000

Data Index: 1106086 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.5733. Min Act: -0.0000

Data Index: 143100 (The Pile)

Max Activating Token Index: 830