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

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

Neuron 812 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.6231. Min Act: -0.0001

Data Index: 978126 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.4820. Min Act: -0.0001

Data Index: 361792 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.3189. Min Act: -0.0001

Data Index: 508231 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.4608. Min Act: -0.0001

Data Index: 473584 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.3365. Min Act: -0.0001

Data Index: 968618 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.2788. Min Act: -0.0001

Data Index: 855884 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.1841. Min Act: -0.0001

Data Index: 383339 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.2111. Min Act: -0.0001

Data Index: 1331581 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.2622. Min Act: -0.0001

Data Index: 420821 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.1437. Min Act: -0.0000

Data Index: 379424 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0962. Min Act: -0.0001

Data Index: 747538 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0650. Min Act: -0.0000

Data Index: 448644 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0414. Min Act: -0.0000

Data Index: 399660 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9606. Min Act: -0.0001

Data Index: 817772 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.1173. Min Act: -0.0001

Data Index: 256885 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0562. Min Act: -0.0001

Data Index: 216754 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0807. Min Act: -0.0001

Data Index: 673114 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0381. Min Act: -0.0001

Data Index: 719369 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0129. Min Act: -0.0000

Data Index: 963146 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0570. Min Act: -0.0000

Data Index: 44051 (C4 (Web Text))

Max Activating Token Index: 504