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

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

Neuron 3555 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: 1.1892. Min Range: -1.1892

Max Act: 1.1892. Min Act: -0.0001

Data Index: 1125773 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.9830. Min Act: -0.0001

Data Index: 264358 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8729. Min Act: -0.0001

Data Index: 648059 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8379. Min Act: -0.0001

Data Index: 700689 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7787. Min Act: -0.0001

Data Index: 739382 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7356. Min Act: -0.0001

Data Index: 182372 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7548. Min Act: -0.0001

Data Index: 925965 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8247. Min Act: -0.0001

Data Index: 613788 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7923. Min Act: -0.0001

Data Index: 976119 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7740. Min Act: -0.0001

Data Index: 432556 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7954. Min Act: -0.0001

Data Index: 1215329 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7853. Min Act: -0.0001

Data Index: 796665 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7460. Min Act: -0.0001

Data Index: 586551 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7479. Min Act: -0.0001

Data Index: 401306 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7814. Min Act: -0.0001

Data Index: 158162 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.6893. Min Act: -0.0001

Data Index: 787117 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1084647 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7088. Min Act: -0.0001

Data Index: 879133 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7217. Min Act: -0.0001

Data Index: 1352719 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7079. Min Act: -0.0001

Data Index: 56380 (C4 (Web Text))

Max Activating Token Index: 162