Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 579 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.1109. Min Act: -0.0001

Data Index: 1096169 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0656. Min Act: -0.0001

Data Index: 1018954 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.1524. Min Act: -0.0001

Data Index: 641603 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.9349. Min Act: -0.0001

Data Index: 1088705 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.8983. Min Act: -0.0001

Data Index: 301840 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.4202. Min Act: -0.0001

Data Index: 363757 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.3552. Min Act: -0.0001

Data Index: 177837 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.5839. Min Act: -0.0001

Data Index: 403820 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.7185. Min Act: -0.0001

Data Index: 251703 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.7030. Min Act: -0.0001

Data Index: 256573 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.8207. Min Act: -0.0001

Data Index: 648227 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.4269. Min Act: -0.0001

Data Index: 371713 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0768. Min Act: -0.0001

Data Index: 50414 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.4165. Min Act: -0.0001

Data Index: 1121902 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.6544. Min Act: -0.0001

Data Index: 232153 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.6613. Min Act: -0.0001

Data Index: 349245 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.7754. Min Act: -0.0001

Data Index: 514326 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.4959. Min Act: -0.0001

Data Index: 465537 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.7603. Min Act: -0.0001

Data Index: 968696 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.7474. Min Act: -0.0001

Data Index: 333045 (C4 (Web Text))

Max Activating Token Index: 307