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

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

Neuron 3185 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4917. Min Act: -0.0000

Data Index: 449246 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.0398. Min Act: -0.0000

Data Index: 314675 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.9838. Min Act: -0.0000

Data Index: 1045418 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.9769. Min Act: -0.0000

Data Index: 678611 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.0179. Min Act: -0.0000

Data Index: 247427 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.8980. Min Act: -0.0000

Data Index: 975380 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.9888. Min Act: -0.0000

Data Index: 792992 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.8754. Min Act: -0.0000

Data Index: 1315555 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.9523. Min Act: -0.0000

Data Index: 879219 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.8330. Min Act: -0.0000

Data Index: 364794 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.8207. Min Act: -0.0000

Data Index: 852988 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.9039. Min Act: -0.0000

Data Index: 711321 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.7661. Min Act: -0.0000

Data Index: 9684 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.7825. Min Act: -0.0000

Data Index: 1227893 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.8936. Min Act: -0.0000

Data Index: 785239 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1054046 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.8440. Min Act: -0.0000

Data Index: 658560 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.6754. Min Act: -0.0000

Data Index: 642041 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.6753. Min Act: -0.0000

Data Index: 316787 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 2.4917. Min Range: -2.4917

Max Act: 1.7552. Min Act: -0.0000

Data Index: 587785 (C4 (Web Text))

Max Activating Token Index: 484