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

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

Neuron 764 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: 0.9175. Min Range: -0.9175

Max Act: 0.9175. Min Act: -0.0000

Data Index: 330391 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.8813. Min Act: -0.0000

Data Index: 905868 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.8277. Min Act: 0.0000

Data Index: 35359 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1255246 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7977. Min Act: -0.0000

Data Index: 587921 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7556. Min Act: -0.0000

Data Index: 693876 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7939. Min Act: -0.0000

Data Index: 657044 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7746. Min Act: -0.0000

Data Index: 165443 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7641. Min Act: -0.0000

Data Index: 338848 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1227839 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7342. Min Act: -0.0000

Data Index: 533992 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1173324 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1305549 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1178836 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1368650 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1311303 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1265970 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7213. Min Act: -0.0000

Data Index: 927410 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7330. Min Act: -0.0000

Data Index: 679210 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1223798 (C4 (Web Text))

Max Activating Token Index: 32