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

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

Neuron 382 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: 0.8591. Min Range: -0.8591

Max Act: 0.8591. Min Act: -0.0002

Data Index: 1150270 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1016817 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7518. Min Act: -0.0001

Data Index: 405273 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.6458. Min Act: -0.0001

Data Index: 484705 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.6184. Min Act: -0.0002

Data Index: 30977 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.6353. Min Act: -0.0001

Data Index: 744670 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7523. Min Act: -0.0001

Data Index: 225788 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.6540. Min Act: -0.0001

Data Index: 361293 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.5790. Min Act: -0.0001

Data Index: 445329 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.6257. Min Act: -0.0001

Data Index: 647420 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.5877. Min Act: -0.0001

Data Index: 531842 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.5717. Min Act: -0.0002

Data Index: 17320 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.5666. Min Act: -0.0001

Data Index: 928774 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.5796. Min Act: -0.0002

Data Index: 998448 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.6672. Min Act: -0.0001

Data Index: 562353 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.5825. Min Act: -0.0001

Data Index: 1349867 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.5975. Min Act: -0.0001

Data Index: 345404 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.5836. Min Act: -0.0002

Data Index: 966286 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.6217. Min Act: -0.0002

Data Index: 779748 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.4887. Min Act: -0.0001

Data Index: 905394 (C4 (Web Text))

Max Activating Token Index: 616