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

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

Neuron 710 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.7707. Min Act: -0.0001

Data Index: 1323065 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.7286. Min Act: -0.0001

Data Index: 414615 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6687. Min Act: -0.0001

Data Index: 1164450 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6285. Min Act: -0.0001

Data Index: 840366 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6245. Min Act: -0.0001

Data Index: 490951 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6474. Min Act: -0.0001

Data Index: 1076071 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5638. Min Act: -0.0001

Data Index: 590748 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5390. Min Act: -0.0001

Data Index: 699453 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6349. Min Act: -0.0001

Data Index: 1343446 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5769. Min Act: -0.0001

Data Index: 794601 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5541. Min Act: -0.0001

Data Index: 1052660 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5370. Min Act: -0.0001

Data Index: 1334783 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5752. Min Act: -0.0001

Data Index: 321828 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5214. Min Act: -0.0001

Data Index: 704904 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5301. Min Act: -0.0001

Data Index: 199457 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5449. Min Act: -0.0001

Data Index: 1336306 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5661. Min Act: -0.0001

Data Index: 283995 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5234. Min Act: -0.0001

Data Index: 399446 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.4941. Min Act: -0.0001

Data Index: 607640 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5076. Min Act: -0.0001

Data Index: 911878 (C4 (Web Text))

Max Activating Token Index: 552