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

Dataset: The Pile

Neuron 3859 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.9610. Min Act: -0.0000

Data Index: 641602 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.0040. Min Act: -0.0000

Data Index: 1828318 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.1084. Min Act: -0.0000

Data Index: 467763 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.2010. Min Act: -0.0000

Data Index: 1489921 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.5140. Min Act: -0.0000

Data Index: 303405 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.9126. Min Act: -0.0000

Data Index: 173691 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.7352. Min Act: -0.0000

Data Index: 1497932 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.1503. Min Act: -0.0000

Data Index: 1614622 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.4180. Min Act: -0.0000

Data Index: 1240607 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.1192. Min Act: -0.0000

Data Index: 205064 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.0186. Min Act: -0.0000

Data Index: 1293994 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.8409. Min Act: -0.0000

Data Index: 89727 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.1126. Min Act: -0.0000

Data Index: 646045 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.0924. Min Act: -0.0000

Data Index: 31835 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.7924. Min Act: -0.0000

Data Index: 1393271 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.7530. Min Act: -0.0000

Data Index: 1198299 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.8690. Min Act: -0.0000

Data Index: 755593 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.8913. Min Act: -0.0000

Data Index: 402489 (The Pile)

Max Activating Token Index: 674

Text #18

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.8909. Min Act: -0.0000

Data Index: 1602187 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.0088. Min Act: -0.0000

Data Index: 1440477 (The Pile)

Max Activating Token Index: 207