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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.4096. Min Act: -0.0000

Data Index: 68938 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.2878. Min Act: -0.0000

Data Index: 231108 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.3842. Min Act: -0.0000

Data Index: 494867 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.3771. Min Act: -0.0000

Data Index: 333683 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.5143. Min Act: -0.0000

Data Index: 8516 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.3294. Min Act: -0.0000

Data Index: 1162880 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.2889. Min Act: -0.0000

Data Index: 718252 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.2898. Min Act: -0.0000

Data Index: 427896 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.3876. Min Act: -0.0000

Data Index: 855845 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.2528. Min Act: 0.0001

Data Index: 123411 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.2061. Min Act: -0.0000

Data Index: 141070 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.0655. Min Act: 0.0000

Data Index: 846276 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.1319. Min Act: -0.0000

Data Index: 1183748 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.1207. Min Act: -0.0000

Data Index: 628241 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.1895. Min Act: -0.0000

Data Index: 115275 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.1783. Min Act: -0.0000

Data Index: 501557 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.1467. Min Act: -0.0000

Data Index: 45192 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.0151. Min Act: -0.0000

Data Index: 128744 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.0058. Min Act: -0.0000

Data Index: 848475 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 2.5143. Min Range: -2.5143

Max Act: 2.1282. Min Act: -0.0000

Data Index: 60132 (C4 (Web Text))

Max Activating Token Index: 348