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

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

Neuron 2740 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4792. Min Act: -0.0000

Data Index: 916286 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4607. Min Act: -0.0001

Data Index: 472857 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4095. Min Act: -0.0001

Data Index: 584808 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4176. Min Act: -0.0001

Data Index: 1034233 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4012. Min Act: -0.0001

Data Index: 1126927 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3534. Min Act: -0.0001

Data Index: 861773 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4032. Min Act: -0.0001

Data Index: 924273 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4056. Min Act: -0.0001

Data Index: 533043 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3827. Min Act: -0.0001

Data Index: 297203 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3625. Min Act: -0.0001

Data Index: 921555 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3801. Min Act: -0.0001

Data Index: 1019883 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3989. Min Act: -0.0001

Data Index: 53124 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3566. Min Act: -0.0001

Data Index: 1344625 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3922. Min Act: -0.0001

Data Index: 619369 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3927. Min Act: -0.0001

Data Index: 1275569 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3270. Min Act: -0.0001

Data Index: 422254 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3535. Min Act: -0.0001

Data Index: 432674 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1140856 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3096. Min Act: -0.0001

Data Index: 1011361 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3380. Min Act: -0.0001

Data Index: 627312 (C4 (Web Text))

Max Activating Token Index: 502