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

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

Neuron 2458 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6587. Min Act: -0.0000

Data Index: 312618 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6409. Min Act: -0.0000

Data Index: 495687 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6231. Min Act: -0.0000

Data Index: 801677 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1004378 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5832. Min Act: -0.0000

Data Index: 571649 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1343316 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1540152 (Python Code)

Max Activating Token Index: 852

Text #7

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5705. Min Act: -0.0000

Data Index: 969660 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5839. Min Act: -0.0000

Data Index: 218996 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5923. Min Act: -0.0000

Data Index: 624662 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5530. Min Act: -0.0000

Data Index: 43865 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1229384 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1400880 (Python Code)

Max Activating Token Index: 496

Text #13

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5004. Min Act: -0.0000

Data Index: 254020 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1185762 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1076426 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5248. Min Act: -0.0000

Data Index: 173217 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4976. Min Act: -0.0000

Data Index: 103371 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5170. Min Act: -0.0000

Data Index: 721565 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5099. Min Act: -0.0000

Data Index: 974710 (C4 (Web Text))

Max Activating Token Index: 280