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

Dataset: The Pile

Neuron 3658 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2874. Min Range: -5.2874

Max Act: 5.2874. Min Act: -0.0000

Data Index: 377 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 5.2874. Min Range: -5.2874

Max Act: 5.1889. Min Act: -0.0000

Data Index: 1136704 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.5232. Min Act: -0.0000

Data Index: 788176 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 5.2874. Min Range: -5.2874

Max Act: 3.9539. Min Act: -0.0000

Data Index: 190586 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.6400. Min Act: -0.0000

Data Index: 1076411 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.0072. Min Act: -0.0000

Data Index: 1859303 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 5.2874. Min Range: -5.2874

Max Act: 3.3177. Min Act: -0.0000

Data Index: 1299294 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.1944. Min Act: -0.0000

Data Index: 190068 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.5486. Min Act: -0.0000

Data Index: 876305 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.0590. Min Act: -0.0000

Data Index: 746601 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.1986. Min Act: -0.0000

Data Index: 1002948 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.2721. Min Act: -0.0000

Data Index: 721627 (The Pile)

Max Activating Token Index: 928

Text #12

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.0901. Min Act: -0.0000

Data Index: 1747708 (The Pile)

Max Activating Token Index: 960

Text #13

Max Range: 5.2874. Min Range: -5.2874

Max Act: 3.7186. Min Act: -0.0000

Data Index: 179109 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 5.2874. Min Range: -5.2874

Max Act: 3.9839. Min Act: -0.0000

Data Index: 321360 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 5.2874. Min Range: -5.2874

Max Act: 3.8292. Min Act: -0.0000

Data Index: 1651404 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 5.2874. Min Range: -5.2874

Max Act: 3.7048. Min Act: -0.0000

Data Index: 1552296 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 5.2874. Min Range: -5.2874

Max Act: 3.9012. Min Act: -0.0000

Data Index: 1631563 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 5.2874. Min Range: -5.2874

Max Act: 4.0537. Min Act: -0.0000

Data Index: 846413 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 5.2874. Min Range: -5.2874

Max Act: 2.9746. Min Act: -0.0000

Data Index: 331472 (The Pile)

Max Activating Token Index: 700