Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.8389. Min Act: -0.0001

Data Index: 1543637 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.8354. Min Act: -0.0001

Data Index: 485006 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7896. Min Act: -0.0001

Data Index: 833041 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6606. Min Act: -0.0001

Data Index: 406779 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.5440. Min Act: -0.0001

Data Index: 136002 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6638. Min Act: -0.0001

Data Index: 1232768 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.4272. Min Act: -0.0001

Data Index: 380226 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.4989. Min Act: -0.0001

Data Index: 1249527 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.2073. Min Act: -0.0001

Data Index: 110046 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.4272. Min Act: -0.0001

Data Index: 918866 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.4260. Min Act: -0.0001

Data Index: 387072 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.5000. Min Act: -0.0001

Data Index: 1271864 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.2773. Min Act: -0.0001

Data Index: 576581 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.2588. Min Act: -0.0001

Data Index: 1114065 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3485. Min Act: -0.0001

Data Index: 754930 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.1246. Min Act: -0.0001

Data Index: 396997 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.2591. Min Act: -0.0001

Data Index: 182522 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3209. Min Act: -0.0001

Data Index: 626307 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3085. Min Act: -0.0001

Data Index: 880153 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3720. Min Act: -0.0001

Data Index: 1558 (C4 (Web Text))

Max Activating Token Index: 124