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

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

Neuron 1503 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4999. Min Act: -0.0001

Data Index: 333467 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.5170. Min Act: -0.0001

Data Index: 394653 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4723. Min Act: -0.0001

Data Index: 520988 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4712. Min Act: -0.0001

Data Index: 340734 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4683. Min Act: -0.0000

Data Index: 156081 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.5080. Min Act: -0.0000

Data Index: 126926 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4437. Min Act: -0.0000

Data Index: 582642 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4323. Min Act: -0.0001

Data Index: 582132 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4405. Min Act: -0.0001

Data Index: 167825 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4342. Min Act: -0.0001

Data Index: 392893 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4178. Min Act: -0.0001

Data Index: 999820 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.4250. Min Act: -0.0001

Data Index: 681028 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3982. Min Act: -0.0000

Data Index: 309689 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3973. Min Act: -0.0001

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1345128 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3601. Min Act: -0.0000

Data Index: 602446 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3871. Min Act: -0.0001

Data Index: 224021 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1195141 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1102 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3000. Min Act: -0.0000

Data Index: 372180 (C4 (Web Text))

Max Activating Token Index: 508