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

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

Neuron 3233 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0203. Min Range: -1.0203

Max Act: 1.0177. Min Act: -0.0000

Data Index: 397868 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.0203. Min Range: -1.0203

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1336750 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 1.0203. Min Range: -1.0203

Max Act: 1.0203. Min Act: -0.0000

Data Index: 464320 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.9941. Min Act: -0.0000

Data Index: 540387 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.9889. Min Act: -0.0000

Data Index: 561114 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1248486 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8642. Min Act: -0.0000

Data Index: 608503 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8237. Min Act: 0.0000

Data Index: 561750 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8399. Min Act: -0.0000

Data Index: 908265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1298342 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1104849 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1185304 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7946. Min Act: -0.0000

Data Index: 256877 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1250913 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7648. Min Act: -0.0000

Data Index: 329817 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7838. Min Act: -0.0000

Data Index: 399480 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7675. Min Act: -0.0000

Data Index: 254784 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7665. Min Act: -0.0000

Data Index: 380724 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7931. Min Act: -0.0000

Data Index: 967363 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7412. Min Act: -0.0000

Data Index: 834399 (C4 (Web Text))

Max Activating Token Index: 767