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

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

Neuron 668 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: 1.4852. Min Range: -1.4852

Max Act: 1.4852. Min Act: -0.0000

Data Index: 840895 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2959. Min Act: -0.0001

Data Index: 539848 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2108. Min Act: -0.0001

Data Index: 210329 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.0335. Min Act: -0.0001

Data Index: 1017613 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.0559. Min Act: -0.0000

Data Index: 446446 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.0344. Min Act: -0.0000

Data Index: 681894 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.0314. Min Act: -0.0000

Data Index: 945134 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.0335. Min Act: -0.0001

Data Index: 888234 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.9209. Min Act: -0.0001

Data Index: 372781 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.9725. Min Act: -0.0001

Data Index: 580720 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.9376. Min Act: -0.0000

Data Index: 65584 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8731. Min Act: -0.0001

Data Index: 1070068 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.9412. Min Act: -0.0001

Data Index: 10760 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.9269. Min Act: -0.0001

Data Index: 466306 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.9567. Min Act: -0.0001

Data Index: 343147 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8254. Min Act: -0.0001

Data Index: 878470 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8539. Min Act: -0.0001

Data Index: 947458 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8030. Min Act: -0.0001

Data Index: 118549 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8723. Min Act: -0.0001

Data Index: 859855 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8391. Min Act: -0.0001

Data Index: 447176 (C4 (Web Text))

Max Activating Token Index: 586