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

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

Neuron 3784 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.7176. Min Act: -0.0000

Data Index: 194124 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1044742 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1030729 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5922. Min Act: -0.0000

Data Index: 77635 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1275219 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5563. Min Act: -0.0000

Data Index: 258510 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1087921 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5523. Min Act: -0.0000

Data Index: 801498 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1187860 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.4999. Min Act: -0.0000

Data Index: 372414 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5335. Min Act: -0.0000

Data Index: 422813 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5244. Min Act: -0.0000

Data Index: 924794 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5248. Min Act: -0.0000

Data Index: 518175 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5226. Min Act: -0.0000

Data Index: 18353 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5284. Min Act: -0.0000

Data Index: 945682 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5288. Min Act: -0.0000

Data Index: 100904 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.4802. Min Act: -0.0000

Data Index: 781987 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1190687 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5080. Min Act: -0.0000

Data Index: 400013 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.7176. Min Range: -0.7176

Max Act: 0.5710. Min Act: -0.0000

Data Index: 215890 (C4 (Web Text))

Max Activating Token Index: 744