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

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

Neuron 5086 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1315. Min Range: -1.1315

Max Act: 1.1315. Min Act: -0.0000

Data Index: 960626 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9894. Min Act: -0.0000

Data Index: 129834 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 1.1315. Min Range: -1.1315

Max Act: 1.0114. Min Act: -0.0000

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9197. Min Act: -0.0000

Data Index: 147827 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8703. Min Act: -0.0000

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1134896 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9115. Min Act: -0.0000

Data Index: 425446 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1317937 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8585. Min Act: -0.0000

Data Index: 301825 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8465. Min Act: -0.0000

Data Index: 72381 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7714. Min Act: -0.0000

Data Index: 254585 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8195. Min Act: -0.0000

Data Index: 662815 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1260396 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7300. Min Act: -0.0000

Data Index: 930712 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7971. Min Act: -0.0000

Data Index: 596236 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7866. Min Act: -0.0000

Data Index: 821813 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1043342 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7314. Min Act: -0.0000

Data Index: 342025 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7346. Min Act: -0.0000

Data Index: 739275 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1236781 (C4 (Web Text))

Max Activating Token Index: 432