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

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

Neuron 1871 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: 0.1660. Min Range: -0.1660

Max Act: 0.1660. Min Act: -0.0000

Data Index: 757732 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1308698 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1332134 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1145774 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1219. Min Act: -0.0000

Data Index: 850004 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1130. Min Act: -0.0000

Data Index: 218438 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1218. Min Act: -0.0000

Data Index: 535707 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1092. Min Act: -0.0000

Data Index: 675723 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1016. Min Act: -0.0000

Data Index: 935473 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1000565 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0920. Min Act: -0.0000

Data Index: 160500 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0937. Min Act: -0.0000

Data Index: 802501 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0925. Min Act: -0.0000

Data Index: 205214 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0953. Min Act: -0.0000

Data Index: 864427 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1099692 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1300620 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0905. Min Act: -0.0000

Data Index: 270474 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0835. Min Act: -0.0000

Data Index: 567067 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1224652 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1297069 (C4 (Web Text))

Max Activating Token Index: 306