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

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

Neuron 3597 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.9384. Min Act: -0.0000

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.7609. Min Act: -0.0000

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1105257 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5790. Min Act: -0.0000

Data Index: 803517 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5963. Min Act: -0.0000

Data Index: 702193 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5185. Min Act: -0.0000

Data Index: 367930 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4633. Min Act: -0.0000

Data Index: 123379 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1118475 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5396. Min Act: -0.0000

Data Index: 809192 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5337. Min Act: -0.0000

Data Index: 1200711 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5339. Min Act: -0.0000

Data Index: 545804 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4351. Min Act: -0.0000

Data Index: 717538 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1189044 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4135. Min Act: -0.0000

Data Index: 713507 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1329747 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4630. Min Act: -0.0000

Data Index: 1265314 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1069102 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.3964. Min Act: -0.0000

Data Index: 464734 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4696. Min Act: -0.0000

Data Index: 796343 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4707. Min Act: -0.0000

Data Index: 602975 (C4 (Web Text))

Max Activating Token Index: 864