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

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

Neuron 3085 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.2114. Min Act: -0.0000

Data Index: 281880 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.2126. Min Act: -0.0000

Data Index: 697783 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.2210. Min Act: -0.0000

Data Index: 590438 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1036444 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1883. Min Act: -0.0000

Data Index: 991249 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1337091 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1591. Min Act: -0.0000

Data Index: 44308 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1616. Min Act: -0.0000

Data Index: 750670 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1539. Min Act: -0.0000

Data Index: 147687 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1079876 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1464. Min Act: -0.0000

Data Index: 145820 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1044668 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1625. Min Act: -0.0000

Data Index: 456451 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1326. Min Act: -0.0000

Data Index: 383332 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1347914 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1380. Min Act: -0.0000

Data Index: 303627 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1468. Min Act: -0.0000

Data Index: 325740 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1161539 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1353. Min Act: -0.0000

Data Index: 743194 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1458. Min Act: -0.0000

Data Index: 205746 (C4 (Web Text))

Max Activating Token Index: 918