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

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

Neuron 1555 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: 3.4161. Min Range: -3.4161

Max Act: 3.4161. Min Act: -0.0000

Data Index: 72548 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 3.4161. Min Range: -3.4161

Max Act: 3.2230. Min Act: -0.0000

Data Index: 62467 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.6394. Min Act: -0.0000

Data Index: 268107 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.7192. Min Act: -0.0000

Data Index: 660053 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.6483. Min Act: -0.0000

Data Index: 340186 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.2291. Min Act: -0.0000

Data Index: 572432 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.4366. Min Act: -0.0000

Data Index: 161795 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.2245. Min Act: -0.0000

Data Index: 872768 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.3383. Min Act: -0.0000

Data Index: 102483 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.0075. Min Act: -0.0000

Data Index: 660305 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 3.4161. Min Range: -3.4161

Max Act: 1.9831. Min Act: -0.0000

Data Index: 1182219 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.2007. Min Act: -0.0000

Data Index: 584879 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.2862. Min Act: -0.0000

Data Index: 618372 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.1399. Min Act: -0.0000

Data Index: 701779 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.2018. Min Act: -0.0000

Data Index: 225902 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.3076. Min Act: -0.0000

Data Index: 176470 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.4158. Min Act: -0.0000

Data Index: 1041896 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.0278. Min Act: -0.0000

Data Index: 1430360 (Python Code)

Max Activating Token Index: 989

Text #18

Max Range: 3.4161. Min Range: -3.4161

Max Act: 2.1570. Min Act: -0.0000

Data Index: 859415 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 3.4161. Min Range: -3.4161

Max Act: 1.8911. Min Act: -0.0000

Data Index: 41937 (C4 (Web Text))

Max Activating Token Index: 899