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

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

Neuron 2346 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5833. Min Act: -0.0000

Data Index: 82699 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1161367 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4553. Min Act: -0.0000

Data Index: 426670 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5036. Min Act: -0.0000

Data Index: 641494 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1355147 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4944. Min Act: -0.0000

Data Index: 964972 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1069449 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4588. Min Act: -0.0000

Data Index: 729821 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1315968 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4437. Min Act: -0.0000

Data Index: 936702 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4165. Min Act: -0.0000

Data Index: 316399 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4949. Min Act: -0.0000

Data Index: 628451 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4691. Min Act: -0.0000

Data Index: 735359 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4347. Min Act: -0.0000

Data Index: 650040 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4284. Min Act: -0.0000

Data Index: 360093 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.3976. Min Act: -0.0000

Data Index: 300046 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4532. Min Act: -0.0000

Data Index: 317160 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4502. Min Act: -0.0000

Data Index: 961957 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1104482 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1124144 (C4 (Web Text))

Max Activating Token Index: 352