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

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

Neuron 2983 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: 0.5640. Min Range: -0.5640

Max Act: 0.5529. Min Act: -0.0001

Data Index: 1299053 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5640. Min Act: -0.0001

Data Index: 312491 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5115. Min Act: -0.0001

Data Index: 663965 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4849. Min Act: -0.0001

Data Index: 869115 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5264. Min Act: -0.0001

Data Index: 920579 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5248. Min Act: -0.0001

Data Index: 1177256 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4750. Min Act: -0.0001

Data Index: 250989 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4865. Min Act: -0.0001

Data Index: 1329236 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5004. Min Act: -0.0001

Data Index: 519143 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4430. Min Act: -0.0001

Data Index: 1106779 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1315382 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4201. Min Act: -0.0001

Data Index: 1332624 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4469. Min Act: -0.0001

Data Index: 445785 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4551. Min Act: -0.0001

Data Index: 1339336 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4357. Min Act: -0.0001

Data Index: 312609 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4519. Min Act: -0.0002

Data Index: 937332 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4443. Min Act: -0.0002

Data Index: 441864 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4119. Min Act: -0.0001

Data Index: 230733 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4103. Min Act: -0.0001

Data Index: 1004763 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3953. Min Act: -0.0002

Data Index: 1032749 (C4 (Web Text))

Max Activating Token Index: 613