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

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

Neuron 819 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: 0.9376. Min Range: -0.9376

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1228615 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.9376. Min Act: -0.0001

Data Index: 83750 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.8138. Min Act: -0.0001

Data Index: 347976 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7385. Min Act: -0.0001

Data Index: 202122 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7250. Min Act: -0.0001

Data Index: 715296 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1277811 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7543. Min Act: -0.0001

Data Index: 130007 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7179. Min Act: -0.0001

Data Index: 325043 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7154. Min Act: -0.0001

Data Index: 1118312 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7268. Min Act: -0.0001

Data Index: 1054956 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7554. Min Act: -0.0001

Data Index: 574263 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7097. Min Act: -0.0001

Data Index: 79710 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.7251. Min Act: -0.0001

Data Index: 394772 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.6797. Min Act: -0.0001

Data Index: 262606 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.6606. Min Act: -0.0001

Data Index: 641062 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.6146. Min Act: -0.0001

Data Index: 776997 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.6271. Min Act: -0.0001

Data Index: 133096 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.5989. Min Act: -0.0001

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.6583. Min Act: -0.0001

Data Index: 1180067 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.9376. Min Range: -0.9376

Max Act: 0.6516. Min Act: -0.0001

Data Index: 1037362 (C4 (Web Text))

Max Activating Token Index: 250