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

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

Neuron 3640 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: 3.6165. Min Range: -3.6165

Max Act: 3.6165. Min Act: -0.0000

Data Index: 1018751 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.1900. Min Act: -0.0000

Data Index: 733666 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.0550. Min Act: -0.0000

Data Index: 1140153 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.9738. Min Act: -0.0000

Data Index: 646622 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.8740. Min Act: -0.0000

Data Index: 984309 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.7980. Min Act: -0.0000

Data Index: 166033 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.7489. Min Act: -0.0000

Data Index: 982499 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.8628. Min Act: -0.0000

Data Index: 160853 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.8838. Min Act: -0.0000

Data Index: 582115 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.7152. Min Act: -0.0000

Data Index: 1053279 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.7214. Min Act: -0.0000

Data Index: 1042145 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.8191. Min Act: -0.0000

Data Index: 972853 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.7246. Min Act: -0.0000

Data Index: 499709 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.7158. Min Act: -0.0000

Data Index: 81216 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.7170. Min Act: -0.0000

Data Index: 1206378 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.4255. Min Act: -0.0000

Data Index: 96644 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.5180. Min Act: -0.0000

Data Index: 771687 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.4453. Min Act: -0.0000

Data Index: 1038909 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.5791. Min Act: -0.0000

Data Index: 419302 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 3.6165. Min Range: -3.6165

Max Act: 2.4284. Min Act: -0.0000

Data Index: 125818 (C4 (Web Text))

Max Activating Token Index: 523