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

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

Neuron 2496 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: 1.0162. Min Range: -1.0162

Max Act: 0.9514. Min Act: -0.0001

Data Index: 38256 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.9517. Min Act: -0.0001

Data Index: 1153530 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.0162. Min Range: -1.0162

Max Act: 1.0068. Min Act: -0.0001

Data Index: 995695 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.0162. Min Range: -1.0162

Max Act: 1.0162. Min Act: -0.0001

Data Index: 750648 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8624. Min Act: -0.0001

Data Index: 611469 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.9599. Min Act: -0.0001

Data Index: 794984 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.9957. Min Act: -0.0001

Data Index: 518842 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8995. Min Act: -0.0001

Data Index: 443458 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.9557. Min Act: -0.0001

Data Index: 659994 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8812. Min Act: -0.0001

Data Index: 553835 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8456. Min Act: -0.0001

Data Index: 908486 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.9430. Min Act: -0.0001

Data Index: 1091969 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8572. Min Act: -0.0001

Data Index: 264969 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8534. Min Act: -0.0001

Data Index: 662693 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8474. Min Act: -0.0001

Data Index: 442520 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8439. Min Act: -0.0001

Data Index: 285381 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8371. Min Act: -0.0001

Data Index: 1104570 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.7638. Min Act: -0.0001

Data Index: 1274115 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.7793. Min Act: -0.0001

Data Index: 598324 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.7544. Min Act: -0.0001

Data Index: 17941 (C4 (Web Text))

Max Activating Token Index: 703