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

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

Neuron 5599 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.8085. Min Act: -0.0000

Data Index: 582821 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.8787. Min Act: -0.0000

Data Index: 1081149 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.8775. Min Act: -0.0000

Data Index: 1312497 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.6346. Min Act: -0.0000

Data Index: 21389 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.7863. Min Act: -0.0000

Data Index: 1087037 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.9736. Min Act: -0.0000

Data Index: 1246451 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.9677. Min Act: -0.0000

Data Index: 229158 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.7638. Min Act: -0.0000

Data Index: 1094071 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.5760. Min Act: -0.0000

Data Index: 24238 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 5.0100. Min Range: -5.0100

Max Act: 5.0100. Min Act: -0.0000

Data Index: 455679 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.4279. Min Act: -0.0000

Data Index: 96584 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.3850. Min Act: -0.0000

Data Index: 329978 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.7131. Min Act: -0.0000

Data Index: 759231 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.5373. Min Act: -0.0000

Data Index: 787993 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.6885. Min Act: -0.0000

Data Index: 712402 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.4584. Min Act: -0.0000

Data Index: 221633 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.6011. Min Act: -0.0000

Data Index: 693865 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.4030. Min Act: -0.0000

Data Index: 1174105 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.3985. Min Act: -0.0000

Data Index: 785756 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 5.0100. Min Range: -5.0100

Max Act: 4.0273. Min Act: -0.0000

Data Index: 1221189 (C4 (Web Text))

Max Activating Token Index: 771