Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3566 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.7563. Min Act: -0.0000

Data Index: 1059799 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.6199. Min Act: -0.0000

Data Index: 701411 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.5196. Min Act: -0.0001

Data Index: 920619 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.3019. Min Act: -0.0001

Data Index: 825563 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.2292. Min Act: -0.0001

Data Index: 989275 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.3958. Min Act: -0.0000

Data Index: 755886 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.0401. Min Act: -0.0000

Data Index: 1249045 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.2082. Min Act: -0.0000

Data Index: 227706 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.0036. Min Act: -0.0000

Data Index: 1098505 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.9972. Min Act: -0.0000

Data Index: 78263 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.9315. Min Act: -0.0000

Data Index: 944898 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.9496. Min Act: -0.0000

Data Index: 776823 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.8933. Min Act: -0.0000

Data Index: 128620 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.0316. Min Act: -0.0000

Data Index: 832041 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.7703. Min Act: -0.0000

Data Index: 918892 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.8726. Min Act: -0.0001

Data Index: 1286880 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.9764. Min Act: -0.0001

Data Index: 877161 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.9651. Min Act: -0.0000

Data Index: 962715 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 2.7563. Min Range: -2.7563

Max Act: 1.8440. Min Act: -0.0000

Data Index: 399082 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 2.7563. Min Range: -2.7563

Max Act: 2.0317. Min Act: -0.0001

Data Index: 410752 (C4 (Web Text))

Max Activating Token Index: 166