Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 450 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.1311. Min Act: -0.0000

Data Index: 986794 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1225164 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0803. Min Act: -0.0000

Data Index: 190962 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1986 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.9854. Min Act: -0.0001

Data Index: 848514 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0080. Min Act: -0.0000

Data Index: 329595 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.9426. Min Act: -0.0000

Data Index: 575920 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.9734. Min Act: -0.0001

Data Index: 653163 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.9948. Min Act: -0.0001

Data Index: 944113 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.9171. Min Act: -0.0001

Data Index: 783012 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.8947. Min Act: -0.0001

Data Index: 383656 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.9194. Min Act: -0.0000

Data Index: 49176 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1150308 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.8348. Min Act: -0.0001

Data Index: 307934 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.8634. Min Act: -0.0001

Data Index: 761483 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1078932 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.7995. Min Act: -0.0000

Data Index: 980845 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1060702 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.8460. Min Act: -0.0000

Data Index: 199564 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.8356. Min Act: -0.0000

Data Index: 912058 (C4 (Web Text))

Max Activating Token Index: 706