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

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

Neuron 662 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1136872 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1235. Min Act: -0.0001

Data Index: 23850 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0836. Min Act: -0.0001

Data Index: 542995 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0685. Min Act: -0.0001

Data Index: 409036 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0650. Min Act: -0.0001

Data Index: 141220 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0611. Min Act: -0.0001

Data Index: 479596 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0610. Min Act: -0.0001

Data Index: 930468 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0600. Min Act: -0.0001

Data Index: 824604 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0589. Min Act: -0.0001

Data Index: 215227 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0599. Min Act: -0.0001

Data Index: 950128 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0596. Min Act: -0.0001

Data Index: 729206 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1138628 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0592. Min Act: -0.0001

Data Index: 345941 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0551. Min Act: -0.0001

Data Index: 87726 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0557. Min Act: -0.0001

Data Index: 178249 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0546. Min Act: -0.0001

Data Index: 200690 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0592. Min Act: -0.0001

Data Index: 725062 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0548. Min Act: -0.0001

Data Index: 419487 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0523. Min Act: -0.0001

Data Index: 592914 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0537. Min Act: -0.0001

Data Index: 49376 (C4 (Web Text))

Max Activating Token Index: 90