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

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

Neuron 1176 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.6798. Min Range: -4.6798

Max Act: 4.6798. Min Act: -0.0000

Data Index: 18552 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 4.6798. Min Range: -4.6798

Max Act: 4.4903. Min Act: -0.0000

Data Index: 188706 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 4.6798. Min Range: -4.6798

Max Act: 4.4292. Min Act: -0.0000

Data Index: 806079 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 4.6798. Min Range: -4.6798

Max Act: 4.1214. Min Act: -0.0000

Data Index: 828097 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 4.6798. Min Range: -4.6798

Max Act: 4.1408. Min Act: -0.0000

Data Index: 402642 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 4.6798. Min Range: -4.6798

Max Act: 4.1257. Min Act: -0.0000

Data Index: 630987 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.9623. Min Act: -0.0000

Data Index: 390520 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.8020. Min Act: -0.0000

Data Index: 212614 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.8201. Min Act: -0.0000

Data Index: 200545 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 4.6798. Min Range: -4.6798

Max Act: 4.0014. Min Act: -0.0000

Data Index: 946400 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.6145. Min Act: -0.0000

Data Index: 1125361 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.7670. Min Act: -0.0000

Data Index: 180053 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.5365. Min Act: -0.0000

Data Index: 322623 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.6795. Min Act: -0.0000

Data Index: 121987 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.6662. Min Act: -0.0000

Data Index: 176830 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.6695. Min Act: -0.0000

Data Index: 780427 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.4889. Min Act: -0.0000

Data Index: 323413 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.6464. Min Act: -0.0000

Data Index: 577173 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.6544. Min Act: -0.0000

Data Index: 607981 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 4.6798. Min Range: -4.6798

Max Act: 3.6606. Min Act: -0.0000

Data Index: 1147184 (C4 (Web Text))

Max Activating Token Index: 644