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

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

Neuron 4344 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.6715. Min Act: -0.0000

Data Index: 73530 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.5718. Min Act: -0.0000

Data Index: 290920 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.4378. Min Act: -0.0000

Data Index: 296697 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.5212. Min Act: -0.0000

Data Index: 951396 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.4673. Min Act: -0.0000

Data Index: 1156620 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.4587. Min Act: -0.0000

Data Index: 574300 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1213660 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.3586. Min Act: -0.0000

Data Index: 865401 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2973. Min Act: -0.0000

Data Index: 979203 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.3190. Min Act: -0.0000

Data Index: 883356 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.3402. Min Act: -0.0000

Data Index: 1092151 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2907. Min Act: -0.0000

Data Index: 1044898 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2875. Min Act: -0.0000

Data Index: 290848 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2801. Min Act: -0.0000

Data Index: 812703 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1499376 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2027. Min Act: -0.0000

Data Index: 950343 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2319. Min Act: -0.0000

Data Index: 595303 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2326. Min Act: -0.0000

Data Index: 971099 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.1778. Min Act: -0.0000

Data Index: 400069 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 1.6715. Min Range: -1.6715

Max Act: 1.2091. Min Act: -0.0000

Data Index: 379243 (C4 (Web Text))

Max Activating Token Index: 450