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

Dataset: The Pile

Neuron 3462 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: 1.6663. Min Range: -1.6663

Max Act: 1.6663. Min Act: -0.0000

Data Index: 248399 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.4449. Min Act: -0.0000

Data Index: 533378 (The Pile)

Max Activating Token Index: 937

Text #2

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1275557 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1308804 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.4678. Min Act: -0.0000

Data Index: 1778697 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.4409. Min Act: -0.0000

Data Index: 987369 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.4481. Min Act: -0.0000

Data Index: 233405 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1114347 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.3960. Min Act: -0.0000

Data Index: 888290 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.3929. Min Act: -0.0000

Data Index: 120353 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.3704. Min Act: -0.0000

Data Index: 1031675 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1426190 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.2936. Min Act: -0.0000

Data Index: 714870 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.3405. Min Act: -0.0000

Data Index: 833678 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1794319 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.2363. Min Act: -0.0000

Data Index: 778605 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.2934. Min Act: -0.0000

Data Index: 396068 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.2929. Min Act: -0.0000

Data Index: 348435 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.2919. Min Act: -0.0000

Data Index: 117123 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.3568. Min Act: -0.0000

Data Index: 139779 (The Pile)

Max Activating Token Index: 254