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

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

Neuron 3201 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.3323. Min Act: -0.0001

Data Index: 759276 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2237. Min Act: -0.0000

Data Index: 551000 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2699. Min Act: -0.0001

Data Index: 940 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2017. Min Act: -0.0000

Data Index: 522592 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0185. Min Act: -0.0001

Data Index: 1177692 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0969. Min Act: -0.0000

Data Index: 581465 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0735. Min Act: -0.0000

Data Index: 813496 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0210. Min Act: -0.0000

Data Index: 1160497 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0841. Min Act: -0.0000

Data Index: 384741 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9892. Min Act: -0.0001

Data Index: 134892 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9841. Min Act: -0.0000

Data Index: 763706 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9741. Min Act: -0.0001

Data Index: 286409 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0047. Min Act: -0.0000

Data Index: 690443 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9367. Min Act: -0.0001

Data Index: 767576 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8493. Min Act: -0.0000

Data Index: 893406 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1303495 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8903. Min Act: -0.0000

Data Index: 316317 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8493. Min Act: -0.0001

Data Index: 444402 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1168715 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9014. Min Act: -0.0001

Data Index: 1043658 (C4 (Web Text))

Max Activating Token Index: 183