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

Dataset: The Pile

Neuron 2111 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4726. Min Range: -5.4726

Max Act: 5.4726. Min Act: -0.0000

Data Index: 792731 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.8741. Min Act: -0.0000

Data Index: 1865209 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.6179. Min Act: -0.0000

Data Index: 927028 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.5813. Min Act: -0.0000

Data Index: 507210 (The Pile)

Max Activating Token Index: 644

Text #4

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.3129. Min Act: -0.0000

Data Index: 1840822 (The Pile)

Max Activating Token Index: 903

Text #5

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.8848. Min Act: -0.0000

Data Index: 1750440 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.4247. Min Act: -0.0000

Data Index: 213145 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.0231. Min Act: -0.0000

Data Index: 437453 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.0134. Min Act: -0.0000

Data Index: 619649 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.0298. Min Act: -0.0000

Data Index: 512868 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.1558. Min Act: -0.0000

Data Index: 844649 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.3407. Min Act: -0.0000

Data Index: 1023610 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.1810. Min Act: -0.0000

Data Index: 1673676 (The Pile)

Max Activating Token Index: 99

Text #13

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.5950. Min Act: -0.0000

Data Index: 1325800 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.9321. Min Act: -0.0000

Data Index: 1419708 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.3929. Min Act: -0.0000

Data Index: 711799 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.1958. Min Act: -0.0000

Data Index: 1391807 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.8085. Min Act: -0.0000

Data Index: 153125 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.4804. Min Act: -0.0000

Data Index: 895378 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.0191. Min Act: -0.0000

Data Index: 537259 (The Pile)

Max Activating Token Index: 856