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

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

Neuron 963 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1483475 (Python Code)

Max Activating Token Index: 784

Text #1

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7355. Min Act: -0.0000

Data Index: 500926 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1522892 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1616772 (Python Code)

Max Activating Token Index: 685

Text #4

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6742. Min Act: -0.0000

Data Index: 571023 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1625078 (Python Code)

Max Activating Token Index: 210

Text #6

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7339. Min Act: -0.0000

Data Index: 727169 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1508687 (Python Code)

Max Activating Token Index: 972

Text #8

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1147326 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1597384 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7304. Min Act: -0.0000

Data Index: 918548 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1616030 (Python Code)

Max Activating Token Index: 860

Text #12

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6443. Min Act: -0.0000

Data Index: 991725 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1568006 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7132. Min Act: -0.0000

Data Index: 767668 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1588406 (Python Code)

Max Activating Token Index: 976

Text #16

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6123. Min Act: -0.0000

Data Index: 463952 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1389021 (Python Code)

Max Activating Token Index: 93

Text #18

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6191. Min Act: -0.0000

Data Index: 866773 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6355. Min Act: -0.0000

Data Index: 73741 (C4 (Web Text))

Max Activating Token Index: 143