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

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

Neuron 1506 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: 2.4836. Min Range: -2.4836

Max Act: 2.3023. Min Act: -0.0000

Data Index: 758448 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.4836. Min Act: -0.0000

Data Index: 467567 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.2602. Min Act: -0.0000

Data Index: 164481 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.3248. Min Act: -0.0000

Data Index: 462262 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.1208. Min Act: -0.0000

Data Index: 106317 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.0314. Min Act: -0.0000

Data Index: 529399 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.8361. Min Act: -0.0000

Data Index: 229871 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.0059. Min Act: -0.0000

Data Index: 915824 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.9921. Min Act: -0.0000

Data Index: 921415 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.8823. Min Act: -0.0000

Data Index: 411794 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7431. Min Act: -0.0000

Data Index: 1282046 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7753. Min Act: -0.0000

Data Index: 1354503 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.8478. Min Act: -0.0000

Data Index: 620314 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7918. Min Act: -0.0000

Data Index: 413492 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.8043. Min Act: -0.0000

Data Index: 1191076 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7692. Min Act: -0.0000

Data Index: 1020358 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.8366. Min Act: -0.0000

Data Index: 201571 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7456. Min Act: -0.0000

Data Index: 725785 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7275. Min Act: -0.0000

Data Index: 1326766 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7159. Min Act: -0.0000

Data Index: 451566 (C4 (Web Text))

Max Activating Token Index: 215