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

Dataset: The Pile

Neuron 2781 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1030561 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1940099 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5902. Min Act: -0.0000

Data Index: 362046 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1050475 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1981035 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5580. Min Act: -0.0000

Data Index: 238633 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5721. Min Act: -0.0000

Data Index: 633127 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5945. Min Act: -0.0000

Data Index: 555542 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1926321 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5441. Min Act: -0.0000

Data Index: 859949 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1633771 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5300. Min Act: -0.0000

Data Index: 568240 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5128. Min Act: -0.0000

Data Index: 455865 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5443. Min Act: -0.0000

Data Index: 856335 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5575. Min Act: -0.0000

Data Index: 981192 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5197. Min Act: -0.0000

Data Index: 884602 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1192223 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1012736 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1254809 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1885534 (The Pile)

Max Activating Token Index: 733