Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1983 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1337262 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0494. Min Act: -0.0003

Data Index: 251213 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1024295 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1103388 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0428. Min Act: -0.0003

Data Index: 190395 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0400. Min Act: -0.0003

Data Index: 69968 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0407. Min Act: -0.0003

Data Index: 193776 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0392. Min Act: -0.0003

Data Index: 157689 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0376. Min Act: -0.0003

Data Index: 201993 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0402. Min Act: -0.0003

Data Index: 133479 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0396. Min Act: -0.0003

Data Index: 967815 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0378. Min Act: -0.0003

Data Index: 427015 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1321479 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0389. Min Act: -0.0003

Data Index: 688051 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1032991 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0378. Min Act: -0.0003

Data Index: 239706 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0379. Min Act: -0.0003

Data Index: 174211 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1222880 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0369. Min Act: -0.0003

Data Index: 265840 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0378. Min Act: -0.0003

Data Index: 240569 (C4 (Web Text))

Max Activating Token Index: 278