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

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

Neuron 635 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0278. Min Range: -8.0278

Max Act: 8.0278. Min Act: -0.0000

Data Index: 349426 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 8.0278. Min Range: -8.0278

Max Act: 7.6488. Min Act: -0.0000

Data Index: 355698 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 8.0278. Min Range: -8.0278

Max Act: 7.1550. Min Act: -0.0000

Data Index: 786763 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 8.0278. Min Range: -8.0278

Max Act: 7.3246. Min Act: -0.0000

Data Index: 760173 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 8.0278. Min Range: -8.0278

Max Act: 7.0106. Min Act: -0.0000

Data Index: 1175539 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.9197. Min Act: -0.0000

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.9530. Min Act: -0.0000

Data Index: 1197348 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.9194. Min Act: -0.0000

Data Index: 411604 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.1259. Min Act: -0.0000

Data Index: 37467 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 8.0278. Min Range: -8.0278

Max Act: 7.0475. Min Act: -0.0000

Data Index: 1333674 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 8.0278. Min Range: -8.0278

Max Act: 5.5254. Min Act: -0.0000

Data Index: 1095535 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.5631. Min Act: -0.0000

Data Index: 624898 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.2949. Min Act: -0.0000

Data Index: 941005 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.6272. Min Act: -0.0000

Data Index: 28776 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 8.0278. Min Range: -8.0278

Max Act: 5.3439. Min Act: -0.0000

Data Index: 451407 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.2038. Min Act: -0.0000

Data Index: 660216 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.2218. Min Act: -0.0000

Data Index: 887752 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.0981. Min Act: -0.0000

Data Index: 424251 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 8.0278. Min Range: -8.0278

Max Act: 6.0629. Min Act: -0.0000

Data Index: 424643 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 8.0278. Min Range: -8.0278

Max Act: 5.7720. Min Act: -0.0000

Data Index: 293169 (C4 (Web Text))

Max Activating Token Index: 209