Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 246 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0287. Min Range: -1.0287

Max Act: 1.0287. Min Act: -0.0001

Data Index: 124096 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9169. Min Act: -0.0001

Data Index: 1206417 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9593. Min Act: -0.0001

Data Index: 1304840 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9823. Min Act: -0.0001

Data Index: 474149 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1024023 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8752. Min Act: -0.0001

Data Index: 957902 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8678. Min Act: 0.0000

Data Index: 17982 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7908. Min Act: -0.0001

Data Index: 479822 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8218. Min Act: -0.0000

Data Index: 171205 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8314. Min Act: 0.0000

Data Index: 1353498 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8193. Min Act: -0.0001

Data Index: 130050 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7711. Min Act: -0.0000

Data Index: 997179 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7955. Min Act: 0.0000

Data Index: 525091 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8169. Min Act: -0.0001

Data Index: 1190656 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1348222 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8054. Min Act: 0.0000

Data Index: 1038220 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7997. Min Act: -0.0001

Data Index: 850143 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7913. Min Act: -0.0001

Data Index: 577122 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1161746 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8116. Min Act: -0.0001

Data Index: 335795 (C4 (Web Text))

Max Activating Token Index: 177