Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3794 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.9284. Min Act: -0.0000

Data Index: 149185 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1343200 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8521. Min Act: -0.0000

Data Index: 151100 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.9114. Min Act: -0.0000

Data Index: 406030 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1029998 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8444. Min Act: -0.0000

Data Index: 332273 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8672. Min Act: -0.0000

Data Index: 560526 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1279730 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8447. Min Act: -0.0000

Data Index: 931372 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8354. Min Act: -0.0000

Data Index: 836718 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1245427 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1136219 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8261. Min Act: -0.0000

Data Index: 855065 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8267. Min Act: -0.0000

Data Index: 94102 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1024730 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8204. Min Act: -0.0000

Data Index: 944299 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8452. Min Act: -0.0000

Data Index: 176139 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8194. Min Act: -0.0000

Data Index: 222605 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1307950 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.9073. Min Act: -0.0000

Data Index: 41568 (C4 (Web Text))

Max Activating Token Index: 895