Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2798 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 10.5652. Min Range: -10.5652

Max Act: 10.0681. Min Act: -0.0001

Data Index: 571389 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 10.5652. Min Range: -10.5652

Max Act: 10.5652. Min Act: -0.0001

Data Index: 492415 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 10.5652. Min Range: -10.5652

Max Act: 9.6550. Min Act: -0.0000

Data Index: 930830 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 10.5652. Min Range: -10.5652

Max Act: 9.6440. Min Act: -0.0001

Data Index: 651018 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 10.5652. Min Range: -10.5652

Max Act: 8.8957. Min Act: -0.0000

Data Index: 1284392 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 10.5652. Min Range: -10.5652

Max Act: 9.2418. Min Act: -0.0000

Data Index: 560602 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 10.5652. Min Range: -10.5652

Max Act: 8.9371. Min Act: -0.0000

Data Index: 173091 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 10.5652. Min Range: -10.5652

Max Act: 8.5385. Min Act: -0.0000

Data Index: 611716 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 10.5652. Min Range: -10.5652

Max Act: 8.3624. Min Act: -0.0000

Data Index: 350740 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 10.5652. Min Range: -10.5652

Max Act: 8.0484. Min Act: -0.0001

Data Index: 1262417 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 10.5652. Min Range: -10.5652

Max Act: 7.1650. Min Act: -0.0001

Data Index: 827028 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 10.5652. Min Range: -10.5652

Max Act: 8.1974. Min Act: 0.0000

Data Index: 475526 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 10.5652. Min Range: -10.5652

Max Act: 8.0719. Min Act: -0.0000

Data Index: 505082 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 10.5652. Min Range: -10.5652

Max Act: 6.2741. Min Act: -0.0001

Data Index: 1419480 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 10.5652. Min Range: -10.5652

Max Act: 8.0986. Min Act: -0.0000

Data Index: 1137922 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 10.5652. Min Range: -10.5652

Max Act: 7.8155. Min Act: -0.0001

Data Index: 171019 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 10.5652. Min Range: -10.5652

Max Act: 6.6286. Min Act: -0.0001

Data Index: 225427 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 10.5652. Min Range: -10.5652

Max Act: 7.0824. Min Act: -0.0000

Data Index: 228817 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 10.5652. Min Range: -10.5652

Max Act: 7.7658. Min Act: -0.0001

Data Index: 1612737 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 10.5652. Min Range: -10.5652

Max Act: 6.0742. Min Act: -0.0000

Data Index: 538041 (C4 (Web Text))

Max Activating Token Index: 347