Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 539 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.1914. Min Range: -4.1914

Max Act: 4.1914. Min Act: -0.0001

Data Index: 175889 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.8172. Min Act: -0.0001

Data Index: 1321786 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.7920. Min Act: -0.0001

Data Index: 517885 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.5438. Min Act: -0.0001

Data Index: 1056044 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.7892. Min Act: -0.0001

Data Index: 1322386 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.3222. Min Act: -0.0001

Data Index: 929802 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.6082. Min Act: -0.0001

Data Index: 1338945 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.4232. Min Act: -0.0001

Data Index: 139701 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.3812. Min Act: -0.0001

Data Index: 745376 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.2173. Min Act: -0.0001

Data Index: 581007 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.3306. Min Act: -0.0001

Data Index: 1165555 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.2007. Min Act: -0.0001

Data Index: 110780 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.0857. Min Act: -0.0001

Data Index: 1225134 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 4.1914. Min Range: -4.1914

Max Act: 2.9360. Min Act: -0.0001

Data Index: 1237165 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 4.1914. Min Range: -4.1914

Max Act: 2.7962. Min Act: -0.0001

Data Index: 238953 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.0588. Min Act: -0.0001

Data Index: 525634 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.1594. Min Act: -0.0001

Data Index: 957637 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.0068. Min Act: -0.0001

Data Index: 1183880 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 4.1914. Min Range: -4.1914

Max Act: 3.0099. Min Act: -0.0001

Data Index: 604237 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 4.1914. Min Range: -4.1914

Max Act: 2.9803. Min Act: -0.0001

Data Index: 31635 (C4 (Web Text))

Max Activating Token Index: 588