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

Dataset: The Pile

Neuron 1399 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: 1.2939. Min Range: -1.2939

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1646119 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1885869 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0819. Min Act: -0.0000

Data Index: 487509 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0401. Min Act: -0.0000

Data Index: 160647 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9418. Min Act: -0.0000

Data Index: 162416 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1812686 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1148594 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9088. Min Act: -0.0000

Data Index: 52666 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1401179 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0894. Min Act: -0.0000

Data Index: 626122 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8215. Min Act: -0.0000

Data Index: 129838 (The Pile)

Max Activating Token Index: 740

Text #11

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9500. Min Act: -0.0000

Data Index: 753620 (The Pile)

Max Activating Token Index: 455

Text #12

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1983564 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1391605 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8048. Min Act: -0.0000

Data Index: 462772 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9316. Min Act: -0.0000

Data Index: 804079 (The Pile)

Max Activating Token Index: 181

Text #16

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1439159 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9186. Min Act: -0.0000

Data Index: 26653 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1417319 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1895010 (The Pile)

Max Activating Token Index: 381