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

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

Neuron 659 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: 0.7772. Min Range: -0.7772

Max Act: 0.7772. Min Act: -0.0002

Data Index: 1100916 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7256. Min Act: -0.0001

Data Index: 713801 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7068. Min Act: -0.0002

Data Index: 450310 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6971. Min Act: -0.0002

Data Index: 153194 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5889. Min Act: -0.0002

Data Index: 879009 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5756. Min Act: -0.0002

Data Index: 709712 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1245007 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5348. Min Act: -0.0001

Data Index: 491169 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5184. Min Act: -0.0001

Data Index: 333105 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5472. Min Act: -0.0002

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5136. Min Act: -0.0002

Data Index: 700159 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5244. Min Act: -0.0002

Data Index: 1353787 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5190. Min Act: -0.0001

Data Index: 974966 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.4939. Min Act: -0.0001

Data Index: 528487 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5295. Min Act: -0.0001

Data Index: 933172 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.4882. Min Act: -0.0002

Data Index: 511087 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.4642. Min Act: -0.0002

Data Index: 1330137 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.4719. Min Act: -0.0002

Data Index: 770537 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.4830. Min Act: -0.0001

Data Index: 725629 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.4647. Min Act: -0.0002

Data Index: 1078141 (C4 (Web Text))

Max Activating Token Index: 648