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

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

Neuron 3906 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.9797. Min Act: 0.0000

Data Index: 725504 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.5649. Min Act: -0.0000

Data Index: 630791 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.4681. Min Act: -0.0000

Data Index: 97472 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1198313 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.5101. Min Act: -0.0000

Data Index: 246644 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.5357. Min Act: -0.0000

Data Index: 786837 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.5408. Min Act: -0.0000

Data Index: 290474 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.4881. Min Act: 0.0000

Data Index: 805714 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1063104 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.3364. Min Act: -0.0000

Data Index: 709347 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.2174. Min Act: -0.0000

Data Index: 388104 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.3435. Min Act: -0.0000

Data Index: 583887 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.2797. Min Act: 0.0000

Data Index: 1125256 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1039140 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.3192. Min Act: -0.0000

Data Index: 806835 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.3333. Min Act: -0.0000

Data Index: 978786 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.2647. Min Act: -0.0000

Data Index: 434321 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1307994 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1091778 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.2433. Min Act: -0.0000

Data Index: 145519 (C4 (Web Text))

Max Activating Token Index: 844