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

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

Neuron 4167 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: 1.3136. Min Range: -1.3136

Max Act: 1.2681. Min Act: -0.0000

Data Index: 246530 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.3136. Min Act: -0.0000

Data Index: 44564 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1502. Min Act: -0.0000

Data Index: 691864 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1264192 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0843. Min Act: -0.0000

Data Index: 543476 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0885. Min Act: -0.0000

Data Index: 291168 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0937. Min Act: -0.0000

Data Index: 107106 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0844. Min Act: -0.0000

Data Index: 352248 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0786. Min Act: -0.0000

Data Index: 93107 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0688. Min Act: -0.0000

Data Index: 36181 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1032. Min Act: -0.0000

Data Index: 96100 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1244724 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1195. Min Act: -0.0000

Data Index: 600265 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0536. Min Act: -0.0000

Data Index: 822718 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1059664 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0517. Min Act: -0.0000

Data Index: 551624 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1146423 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0751. Min Act: -0.0000

Data Index: 963909 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0398. Min Act: -0.0000

Data Index: 103094 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0710. Min Act: -0.0000

Data Index: 981779 (C4 (Web Text))

Max Activating Token Index: 956