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

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

Neuron 1025 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3214. Min Range: -2.3214

Max Act: 2.3214. Min Act: -0.0001

Data Index: 347261 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 2.3214. Min Range: -2.3214

Max Act: 2.1917. Min Act: -0.0000

Data Index: 422596 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.9742. Min Act: -0.0000

Data Index: 816573 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.7768. Min Act: -0.0001

Data Index: 1095547 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.8064. Min Act: -0.0001

Data Index: 1093464 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.7909. Min Act: -0.0000

Data Index: 1061367 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.6156. Min Act: -0.0000

Data Index: 657457 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.8200. Min Act: -0.0000

Data Index: 703278 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.8170. Min Act: -0.0001

Data Index: 193354 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.7317. Min Act: -0.0000

Data Index: 648322 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.7292. Min Act: -0.0001

Data Index: 525118 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.6924. Min Act: -0.0001

Data Index: 1252403 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.6747. Min Act: -0.0000

Data Index: 239691 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1246558 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.5673. Min Act: -0.0001

Data Index: 26461 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.6175. Min Act: -0.0001

Data Index: 1029884 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.5114. Min Act: -0.0000

Data Index: 586770 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.6391. Min Act: -0.0000

Data Index: 988040 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.6778. Min Act: -0.0000

Data Index: 347893 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 2.3214. Min Range: -2.3214

Max Act: 1.5824. Min Act: -0.0000

Data Index: 205406 (C4 (Web Text))

Max Activating Token Index: 93