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

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

Neuron 3627 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7541. Min Act: -0.0002

Data Index: 991282 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5969. Min Act: -0.0001

Data Index: 1320861 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4828. Min Act: -0.0002

Data Index: 116267 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5956. Min Act: -0.0001

Data Index: 856895 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5692. Min Act: -0.0002

Data Index: 931677 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5752. Min Act: -0.0002

Data Index: 182631 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6024. Min Act: -0.0002

Data Index: 293499 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6069. Min Act: -0.0002

Data Index: 317413 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5998. Min Act: -0.0001

Data Index: 827794 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5607. Min Act: -0.0002

Data Index: 759687 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6501. Min Act: -0.0002

Data Index: 904743 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5534. Min Act: -0.0002

Data Index: 896520 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5882. Min Act: -0.0002

Data Index: 1148195 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5765. Min Act: -0.0002

Data Index: 208544 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6150. Min Act: -0.0001

Data Index: 765092 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5448. Min Act: -0.0002

Data Index: 244918 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5609. Min Act: -0.0001

Data Index: 375294 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5396. Min Act: -0.0002

Data Index: 865789 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5905. Min Act: -0.0001

Data Index: 742921 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5272. Min Act: -0.0001

Data Index: 902442 (C4 (Web Text))

Max Activating Token Index: 208