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

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

Neuron 1067 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2918. Min Act: -0.0001

Data Index: 348625 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2738. Min Act: -0.0001

Data Index: 98520 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2694. Min Act: -0.0001

Data Index: 356184 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2458. Min Act: -0.0001

Data Index: 114801 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2418. Min Act: -0.0001

Data Index: 397787 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2405. Min Act: -0.0001

Data Index: 158623 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2344. Min Act: -0.0001

Data Index: 804212 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1048385 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2405. Min Act: -0.0001

Data Index: 532228 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2222. Min Act: -0.0001

Data Index: 57385 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2275. Min Act: -0.0001

Data Index: 1163249 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2223. Min Act: -0.0001

Data Index: 887771 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1288049 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2009. Min Act: -0.0001

Data Index: 1942 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2076. Min Act: -0.0001

Data Index: 174671 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2032. Min Act: -0.0001

Data Index: 396700 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1004420 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2039. Min Act: -0.0001

Data Index: 987809 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2039. Min Act: -0.0001

Data Index: 1265083 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1939. Min Act: -0.0001

Data Index: 185311 (C4 (Web Text))

Max Activating Token Index: 47