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

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

Neuron 1769 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2118. Min Range: -1.2118

Max Act: 1.2118. Min Act: -0.0000

Data Index: 777880 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.9450. Min Act: -0.0000

Data Index: 396183 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.8665. Min Act: -0.0000

Data Index: 918400 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.8030. Min Act: -0.0000

Data Index: 339521 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1311450 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7885. Min Act: -0.0000

Data Index: 584429 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7816. Min Act: -0.0000

Data Index: 908658 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.8478. Min Act: -0.0000

Data Index: 765775 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7398. Min Act: -0.0000

Data Index: 311681 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7615. Min Act: -0.0000

Data Index: 755011 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7397. Min Act: -0.0000

Data Index: 110553 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7145. Min Act: -0.0000

Data Index: 747009 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.6994. Min Act: -0.0000

Data Index: 395280 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7244. Min Act: -0.0000

Data Index: 787138 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7214. Min Act: -0.0000

Data Index: 568653 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7112. Min Act: -0.0000

Data Index: 677649 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7216. Min Act: -0.0000

Data Index: 809305 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7186. Min Act: 0.0000

Data Index: 826615 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.6705. Min Act: -0.0000

Data Index: 792825 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.6760. Min Act: -0.0000

Data Index: 977051 (C4 (Web Text))

Max Activating Token Index: 201