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

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

Neuron 3968 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.8838. Min Act: -0.0001

Data Index: 827446 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6784. Min Act: -0.0001

Data Index: 237921 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6899. Min Act: -0.0001

Data Index: 718676 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6362. Min Act: -0.0001

Data Index: 374551 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.7200. Min Act: -0.0001

Data Index: 12083 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6691. Min Act: -0.0001

Data Index: 198187 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5902. Min Act: -0.0001

Data Index: 22883 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6244. Min Act: -0.0001

Data Index: 199648 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6132. Min Act: -0.0001

Data Index: 227985 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6076. Min Act: -0.0001

Data Index: 336210 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6080. Min Act: -0.0001

Data Index: 598498 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5572. Min Act: -0.0001

Data Index: 1241265 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5632. Min Act: -0.0001

Data Index: 689162 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5968. Min Act: -0.0001

Data Index: 329534 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5764. Min Act: -0.0001

Data Index: 1044951 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6345. Min Act: -0.0001

Data Index: 635893 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6234. Min Act: -0.0001

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5798. Min Act: -0.0001

Data Index: 330293 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5982. Min Act: -0.0001

Data Index: 247208 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5625. Min Act: -0.0001

Data Index: 1074957 (C4 (Web Text))

Max Activating Token Index: 441