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

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

Neuron 4085 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2629. Min Range: -2.2629

Max Act: 2.2629. Min Act: -0.0000

Data Index: 300742 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 2.2629. Min Range: -2.2629

Max Act: 2.1355. Min Act: -0.0000

Data Index: 1437956 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 2.2629. Min Range: -2.2629

Max Act: 2.0071. Min Act: -0.0000

Data Index: 1023729 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.9376. Min Act: -0.0000

Data Index: 643374 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7026. Min Act: -0.0000

Data Index: 1545354 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.8957. Min Act: -0.0000

Data Index: 1039838 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7301. Min Act: -0.0000

Data Index: 1324203 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.8080. Min Act: -0.0000

Data Index: 636467 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7608. Min Act: -0.0000

Data Index: 1135276 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7084. Min Act: -0.0000

Data Index: 1431563 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7497. Min Act: -0.0000

Data Index: 817317 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7518. Min Act: -0.0000

Data Index: 1095430 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7264. Min Act: -0.0000

Data Index: 133380 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7154. Min Act: -0.0000

Data Index: 305073 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7762. Min Act: -0.0000

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.7170. Min Act: -0.0000

Data Index: 109827 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.6954. Min Act: -0.0000

Data Index: 827703 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.6975. Min Act: -0.0000

Data Index: 337737 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.6914. Min Act: -0.0000

Data Index: 861161 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 2.2629. Min Range: -2.2629

Max Act: 1.6863. Min Act: -0.0000

Data Index: 180396 (C4 (Web Text))

Max Activating Token Index: 150