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

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

Neuron 2455 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9637. Min Range: -2.9637

Max Act: 2.9637. Min Act: -0.0000

Data Index: 860213 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 2.9637. Min Range: -2.9637

Max Act: 2.4225. Min Act: -0.0000

Data Index: 467679 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 2.9637. Min Range: -2.9637

Max Act: 2.1092. Min Act: -0.0000

Data Index: 661441 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.9527. Min Act: -0.0000

Data Index: 842370 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.9418. Min Act: -0.0000

Data Index: 949958 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 2.9637. Min Range: -2.9637

Max Act: 2.0346. Min Act: -0.0000

Data Index: 693700 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 2.9637. Min Range: -2.9637

Max Act: 2.0287. Min Act: -0.0000

Data Index: 674872 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.9806. Min Act: -0.0000

Data Index: 609714 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.8609. Min Act: -0.0000

Data Index: 182050 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.8712. Min Act: -0.0000

Data Index: 1197531 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.9071. Min Act: -0.0000

Data Index: 730767 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.8732. Min Act: -0.0000

Data Index: 565652 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.8527. Min Act: -0.0000

Data Index: 718613 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.8060. Min Act: -0.0000

Data Index: 1218735 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.7087. Min Act: -0.0000

Data Index: 747815 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.7922. Min Act: -0.0000

Data Index: 713510 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.6430. Min Act: -0.0000

Data Index: 418466 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.7158. Min Act: -0.0000

Data Index: 1119139 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.7300. Min Act: -0.0000

Data Index: 1222234 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.8011. Min Act: -0.0000

Data Index: 946729 (C4 (Web Text))

Max Activating Token Index: 347