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

Dataset: The Pile

Neuron 1475 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: 1.9937. Min Range: -1.9937

Max Act: 1.9398. Min Act: -0.0000

Data Index: 839588 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.9226. Min Act: -0.0000

Data Index: 233769 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.9937. Min Act: -0.0000

Data Index: 825672 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.7855. Min Act: -0.0000

Data Index: 508747 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.8381. Min Act: -0.0000

Data Index: 1337820 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.8246. Min Act: -0.0000

Data Index: 1779940 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.7724. Min Act: -0.0000

Data Index: 1190654 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.7199. Min Act: -0.0000

Data Index: 1210172 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.7049. Min Act: -0.0000

Data Index: 1663268 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.5971. Min Act: -0.0000

Data Index: 1591880 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.7777. Min Act: -0.0000

Data Index: 1111167 (The Pile)

Max Activating Token Index: 994

Text #11

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.5672. Min Act: -0.0000

Data Index: 985590 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1465571 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.5507. Min Act: -0.0000

Data Index: 1061733 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.6528. Min Act: -0.0000

Data Index: 244641 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.6347. Min Act: -0.0000

Data Index: 1864913 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.7308. Min Act: -0.0000

Data Index: 828829 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.6846. Min Act: -0.0000

Data Index: 980554 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.4223. Min Act: -0.0000

Data Index: 91890 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 1.9937. Min Range: -1.9937

Max Act: 1.5770. Min Act: -0.0000

Data Index: 951080 (The Pile)

Max Activating Token Index: 434