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

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

Neuron 3669 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.7737. Min Act: -0.0002

Data Index: 406449 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5614. Min Act: -0.0002

Data Index: 336059 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5174. Min Act: -0.0002

Data Index: 651538 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5259. Min Act: -0.0002

Data Index: 699046 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5285. Min Act: -0.0002

Data Index: 1186915 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5694. Min Act: -0.0002

Data Index: 582281 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5079. Min Act: -0.0002

Data Index: 149079 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4216. Min Act: -0.0002

Data Index: 1074818 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5506. Min Act: -0.0002

Data Index: 241481 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3925. Min Act: -0.0002

Data Index: 712290 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3282. Min Act: -0.0002

Data Index: 225914 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3268. Min Act: -0.0002

Data Index: 1328596 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3263. Min Act: -0.0002

Data Index: 1200544 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3520. Min Act: -0.0002

Data Index: 160706 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.1980. Min Act: -0.0002

Data Index: 989135 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.2059. Min Act: -0.0002

Data Index: 841877 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3744. Min Act: -0.0002

Data Index: 581663 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3788. Min Act: -0.0002

Data Index: 944351 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.2594. Min Act: -0.0002

Data Index: 743668 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4598. Min Act: -0.0002

Data Index: 385112 (C4 (Web Text))

Max Activating Token Index: 589