Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 786 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2300. Min Range: -1.2300

Max Act: 1.2300. Min Act: -0.0000

Data Index: 80437 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.2300. Min Range: -1.2300

Max Act: 1.1684. Min Act: -0.0000

Data Index: 1123944 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.2300. Min Range: -1.2300

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1097978 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.2300. Min Range: -1.2300

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1328994 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8500. Min Act: 0.0000

Data Index: 1279116 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1153727 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1293584 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8568. Min Act: -0.0000

Data Index: 16120 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1386009 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7801. Min Act: -0.0000

Data Index: 181129 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7987. Min Act: -0.0000

Data Index: 197030 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8154. Min Act: -0.0000

Data Index: 519470 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7357. Min Act: -0.0000

Data Index: 47101 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.6408. Min Act: -0.0000

Data Index: 614235 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.6793. Min Act: -0.0000

Data Index: 777925 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7221. Min Act: -0.0000

Data Index: 76447 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7349. Min Act: -0.0000

Data Index: 522621 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.6917. Min Act: -0.0000

Data Index: 728453 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.6924. Min Act: -0.0000

Data Index: 831624 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1497575 (Python Code)

Max Activating Token Index: 334