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

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

Neuron 3212 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.9216. Min Act: -0.0000

Data Index: 98710 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8704. Min Act: -0.0000

Data Index: 640219 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8912. Min Act: -0.0000

Data Index: 753613 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8988. Min Act: -0.0000

Data Index: 753539 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8161. Min Act: -0.0000

Data Index: 558750 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1271384 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7419. Min Act: -0.0000

Data Index: 621444 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7485. Min Act: -0.0000

Data Index: 81231 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7165. Min Act: -0.0000

Data Index: 827734 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7716. Min Act: -0.0000

Data Index: 323145 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1225446 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7606. Min Act: -0.0000

Data Index: 690059 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7011. Min Act: -0.0000

Data Index: 245708 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1247092 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7088. Min Act: -0.0000

Data Index: 269495 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1151194 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6813. Min Act: -0.0000

Data Index: 723464 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7293. Min Act: -0.0000

Data Index: 308746 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7039. Min Act: -0.0000

Data Index: 466392 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6913. Min Act: -0.0000

Data Index: 108369 (C4 (Web Text))

Max Activating Token Index: 241