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

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

Neuron 4070 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.9564. Min Act: -0.0000

Data Index: 703703 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.6177. Min Act: -0.0000

Data Index: 1215125 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.4850. Min Act: -0.0000

Data Index: 90286 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.4954. Min Act: -0.0000

Data Index: 907331 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.4025. Min Act: -0.0000

Data Index: 170585 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.2166. Min Act: -0.0000

Data Index: 906103 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.4235. Min Act: -0.0000

Data Index: 1125546 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.2828. Min Act: -0.0000

Data Index: 1336499 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.0266. Min Act: -0.0000

Data Index: 800413 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.1382. Min Act: -0.0000

Data Index: 22593 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.1125. Min Act: -0.0000

Data Index: 1232359 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.0204. Min Act: -0.0000

Data Index: 1291623 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.0136. Min Act: -0.0000

Data Index: 655390 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 2.9564. Min Range: -2.9564

Max Act: 1.9793. Min Act: -0.0000

Data Index: 1121423 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 2.9564. Min Range: -2.9564

Max Act: 1.9807. Min Act: -0.0000

Data Index: 245024 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 2.9564. Min Range: -2.9564

Max Act: 1.9379. Min Act: -0.0000

Data Index: 203117 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.0241. Min Act: -0.0000

Data Index: 1183804 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 2.9564. Min Range: -2.9564

Max Act: 1.9006. Min Act: -0.0000

Data Index: 874691 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 2.9564. Min Range: -2.9564

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1294402 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 2.9564. Min Range: -2.9564

Max Act: 2.0001. Min Act: -0.0000

Data Index: 81174 (C4 (Web Text))

Max Activating Token Index: 186