Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1052 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5100. Min Range: -3.5100

Max Act: 3.5100. Min Act: -0.0000

Data Index: 1075432 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 3.5100. Min Range: -3.5100

Max Act: 3.2307. Min Act: -0.0000

Data Index: 733977 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 3.5100. Min Range: -3.5100

Max Act: 3.3138. Min Act: -0.0000

Data Index: 767156 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.9139. Min Act: -0.0000

Data Index: 1030979 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.8390. Min Act: -0.0000

Data Index: 832915 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.9374. Min Act: -0.0000

Data Index: 245185 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.5062. Min Act: -0.0000

Data Index: 317566 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.4316. Min Act: -0.0000

Data Index: 867520 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.4703. Min Act: -0.0000

Data Index: 717931 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.4737. Min Act: -0.0000

Data Index: 649502 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.2670. Min Act: -0.0000

Data Index: 779831 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.4788. Min Act: -0.0000

Data Index: 569191 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.1069. Min Act: -0.0000

Data Index: 27443 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.2210. Min Act: -0.0000

Data Index: 273204 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.0504. Min Act: -0.0000

Data Index: 500359 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.1320. Min Act: -0.0000

Data Index: 59493 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.1580. Min Act: -0.0000

Data Index: 815197 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.3456. Min Act: -0.0000

Data Index: 601546 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 3.5100. Min Range: -3.5100

Max Act: 1.8834. Min Act: -0.0000

Data Index: 991400 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 3.5100. Min Range: -3.5100

Max Act: 2.0145. Min Act: -0.0000

Data Index: 1137401 (C4 (Web Text))

Max Activating Token Index: 881