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

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

Neuron 3329 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1644014 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1416795 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9467. Min Act: -0.0000

Data Index: 354801 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1377322 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8912. Min Act: -0.0000

Data Index: 528274 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1588066 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1632863 (Python Code)

Max Activating Token Index: 459

Text #7

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1428258 (Python Code)

Max Activating Token Index: 372

Text #8

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1546401 (Python Code)

Max Activating Token Index: 885

Text #9

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1050948 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7877. Min Act: -0.0000

Data Index: 477205 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8502. Min Act: -0.0000

Data Index: 563655 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1154925 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1415141 (Python Code)

Max Activating Token Index: 226

Text #14

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1551296 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1383392 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1487816 (Python Code)

Max Activating Token Index: 220

Text #17

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1445488 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1519556 (Python Code)

Max Activating Token Index: 717

Text #19

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6230. Min Act: -0.0000

Data Index: 774721 (C4 (Web Text))

Max Activating Token Index: 652