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

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

Neuron 4240 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.8360. Min Act: -0.0001

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7369. Min Act: -0.0000

Data Index: 92104 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1008204 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1176823 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1175297 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7627. Min Act: -0.0000

Data Index: 911142 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1312439 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7134. Min Act: -0.0001

Data Index: 424594 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7282. Min Act: -0.0000

Data Index: 738359 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6677. Min Act: -0.0000

Data Index: 55275 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6817. Min Act: -0.0000

Data Index: 400006 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1217864 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6873. Min Act: -0.0000

Data Index: 844641 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6810. Min Act: -0.0000

Data Index: 411511 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1096520 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1198699 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1349958 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6825. Min Act: -0.0000

Data Index: 890498 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6538. Min Act: -0.0000

Data Index: 669616 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1189002 (C4 (Web Text))

Max Activating Token Index: 816