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

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

Neuron 5051 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1069656 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4270. Min Act: -0.0000

Data Index: 266742 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3546. Min Act: -0.0000

Data Index: 770769 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1055451 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3424. Min Act: -0.0000

Data Index: 70682 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3235. Min Act: -0.0000

Data Index: 799569 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3233. Min Act: -0.0000

Data Index: 852886 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3326. Min Act: -0.0000

Data Index: 818820 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1143725 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3122. Min Act: -0.0000

Data Index: 62488 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2869. Min Act: -0.0000

Data Index: 233285 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2833. Min Act: -0.0000

Data Index: 380288 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2789. Min Act: -0.0000

Data Index: 120058 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2777. Min Act: 0.0000

Data Index: 1058641 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2885. Min Act: -0.0000

Data Index: 889765 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2923. Min Act: -0.0000

Data Index: 911651 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2773. Min Act: -0.0000

Data Index: 527584 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1583565 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2738. Min Act: -0.0000

Data Index: 106726 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.2789. Min Act: -0.0000

Data Index: 653477 (C4 (Web Text))

Max Activating Token Index: 431