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

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

Neuron 4815 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0001

Data Index: 816612 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0638. Min Act: -0.0001

Data Index: 193847 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1315016 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0602. Min Act: -0.0001

Data Index: 386510 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0582. Min Act: -0.0001

Data Index: 147254 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0578. Min Act: -0.0001

Data Index: 105523 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0580. Min Act: -0.0001

Data Index: 457729 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1063899 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0579. Min Act: -0.0001

Data Index: 976835 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1177870 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0567. Min Act: -0.0001

Data Index: 242906 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1148990 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1137335 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0555. Min Act: -0.0001

Data Index: 1130613 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1059711 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0544. Min Act: -0.0001

Data Index: 827673 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0550. Min Act: -0.0001

Data Index: 964752 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0556. Min Act: -0.0001

Data Index: 82703 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0548. Min Act: -0.0001

Data Index: 99280 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1193572 (C4 (Web Text))

Max Activating Token Index: 94