Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2278 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.8352. Min Act: -0.0003

Data Index: 352153 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.4730. Min Act: -0.0003

Data Index: 39645 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.4524. Min Act: -0.0003

Data Index: 961993 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3380. Min Act: -0.0003

Data Index: 966862 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3731. Min Act: -0.0003

Data Index: 1084875 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3185. Min Act: -0.0003

Data Index: 838997 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3613. Min Act: -0.0003

Data Index: 815808 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3432. Min Act: -0.0003

Data Index: 414655 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3744. Min Act: -0.0003

Data Index: 976731 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2205. Min Act: -0.0003

Data Index: 693671 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3253. Min Act: -0.0003

Data Index: 796980 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.1642. Min Act: -0.0003

Data Index: 911711 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2783. Min Act: -0.0003

Data Index: 275375 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2010. Min Act: -0.0003

Data Index: 79547 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2219. Min Act: -0.0003

Data Index: 853219 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2135. Min Act: -0.0003

Data Index: 1176127 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2175. Min Act: -0.0003

Data Index: 692666 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2166. Min Act: -0.0003

Data Index: 456339 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2497. Min Act: -0.0003

Data Index: 1203915 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.1759. Min Act: -0.0003

Data Index: 387906 (C4 (Web Text))

Max Activating Token Index: 161