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

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

Neuron 278 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7206. Min Range: -6.7206

Max Act: 6.6606. Min Act: -0.0000

Data Index: 745286 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 6.7206. Min Range: -6.7206

Max Act: 6.7206. Min Act: -0.0000

Data Index: 1075317 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 6.7206. Min Range: -6.7206

Max Act: 6.3954. Min Act: -0.0000

Data Index: 649567 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 6.7206. Min Range: -6.7206

Max Act: 6.3329. Min Act: -0.0000

Data Index: 890601 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.8839. Min Act: -0.0000

Data Index: 789004 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.7155. Min Act: -0.0000

Data Index: 451401 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.8335. Min Act: -0.0000

Data Index: 825244 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.6132. Min Act: -0.0000

Data Index: 933893 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.8253. Min Act: -0.0000

Data Index: 1177215 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.7026. Min Act: -0.0000

Data Index: 667519 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.9606. Min Act: -0.0000

Data Index: 221287 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.7079. Min Act: -0.0000

Data Index: 77630 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.6617. Min Act: -0.0000

Data Index: 1293851 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.4002. Min Act: -0.0000

Data Index: 588033 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.5907. Min Act: -0.0000

Data Index: 295974 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.5973. Min Act: -0.0000

Data Index: 553566 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.7183. Min Act: -0.0000

Data Index: 214510 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.4736. Min Act: -0.0000

Data Index: 680477 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.6766. Min Act: -0.0000

Data Index: 75638 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 6.7206. Min Range: -6.7206

Max Act: 5.2854. Min Act: -0.0000

Data Index: 298689 (C4 (Web Text))

Max Activating Token Index: 294