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

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

Neuron 4091 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2795. Min Act: -0.0000

Data Index: 122831 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2881. Min Act: -0.0000

Data Index: 542228 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2747. Min Act: -0.0000

Data Index: 729210 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2806. Min Act: -0.0000

Data Index: 510816 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2635. Min Act: -0.0000

Data Index: 699813 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2665. Min Act: -0.0000

Data Index: 737980 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1216577 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2594. Min Act: -0.0000

Data Index: 756714 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2474. Min Act: -0.0000

Data Index: 593777 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2228. Min Act: -0.0000

Data Index: 294526 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2460. Min Act: -0.0000

Data Index: 290498 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2462. Min Act: -0.0000

Data Index: 590568 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2337. Min Act: -0.0000

Data Index: 389773 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2413. Min Act: -0.0000

Data Index: 830646 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2404. Min Act: -0.0000

Data Index: 401903 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2284. Min Act: -0.0000

Data Index: 407628 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2428. Min Act: -0.0000

Data Index: 478424 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2288. Min Act: -0.0000

Data Index: 684686 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1084725 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2195. Min Act: -0.0000

Data Index: 32668 (C4 (Web Text))

Max Activating Token Index: 91