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

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

Neuron 366 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: 0.9363. Min Range: -0.9363

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1022149 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7019. Min Act: -0.0000

Data Index: 237823 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6995. Min Act: -0.0000

Data Index: 196333 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6174. Min Act: -0.0000

Data Index: 931654 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6153. Min Act: -0.0000

Data Index: 47725 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1099312 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6230. Min Act: -0.0001

Data Index: 106690 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1000607 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1291026 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1305070 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6084. Min Act: -0.0001

Data Index: 790328 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6045. Min Act: -0.0000

Data Index: 610697 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1129315 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1326402 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5660. Min Act: -0.0000

Data Index: 781976 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5652. Min Act: -0.0000

Data Index: 828467 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1000746 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5928. Min Act: -0.0000

Data Index: 890826 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5889. Min Act: -0.0000

Data Index: 317649 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5716. Min Act: -0.0000

Data Index: 402474 (C4 (Web Text))

Max Activating Token Index: 847