Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1344 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0002

Data Index: 20257 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0179. Min Act: -0.0002

Data Index: 310754 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0169. Min Act: -0.0002

Data Index: 362054 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0171. Min Act: -0.0002

Data Index: 100184 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0176. Min Act: -0.0002

Data Index: 467194 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1627386 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0152. Min Act: -0.0002

Data Index: 101219 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1630450 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0142. Min Act: -0.0002

Data Index: 985546 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1483362 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0145. Min Act: -0.0002

Data Index: 547603 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0145. Min Act: -0.0002

Data Index: 660256 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1404240 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0145. Min Act: -0.0002

Data Index: 857708 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0145. Min Act: -0.0002

Data Index: 98235 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0136. Min Act: -0.0002

Data Index: 820430 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0141. Min Act: -0.0002

Data Index: 630031 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1132028 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0136. Min Act: -0.0002

Data Index: 897853 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0140. Min Act: -0.0002

Data Index: 576174 (C4 (Web Text))

Max Activating Token Index: 708