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

Dataset: The Pile

Neuron 4676 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: 1.4954. Min Range: -1.4954

Max Act: 1.4954. Min Act: -0.0000

Data Index: 283875 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4875. Min Act: -0.0000

Data Index: 1880650 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4906. Min Act: -0.0000

Data Index: 211421 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 1.4954. Min Range: -1.4954

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1643500 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2634. Min Act: -0.0000

Data Index: 525710 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2599. Min Act: -0.0000

Data Index: 624987 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1602172 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1520771 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1123361 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1990481 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1898156 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0185. Min Act: -0.0000

Data Index: 206235 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1066. Min Act: -0.0000

Data Index: 253646 (The Pile)

Max Activating Token Index: 225

Text #13

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1525906 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1442660 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1420530 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0593. Min Act: -0.0000

Data Index: 833614 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0512. Min Act: -0.0000

Data Index: 172854 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1126. Min Act: -0.0000

Data Index: 363759 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0481. Min Act: -0.0000

Data Index: 97909 (The Pile)

Max Activating Token Index: 326