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

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

Neuron 1731 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: 4.6127. Min Range: -4.6127

Max Act: 4.6127. Min Act: -0.0000

Data Index: 1307713 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 4.6127. Min Range: -4.6127

Max Act: 3.8959. Min Act: -0.0000

Data Index: 52672 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 4.6127. Min Range: -4.6127

Max Act: 3.4689. Min Act: -0.0000

Data Index: 904671 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 4.6127. Min Range: -4.6127

Max Act: 3.1903. Min Act: -0.0000

Data Index: 979589 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 4.6127. Min Range: -4.6127

Max Act: 3.4792. Min Act: -0.0000

Data Index: 1050360 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 4.6127. Min Range: -4.6127

Max Act: 3.3606. Min Act: 0.0000

Data Index: 541000 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 4.6127. Min Range: -4.6127

Max Act: 3.0357. Min Act: 0.0000

Data Index: 1325546 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.9562. Min Act: -0.0000

Data Index: 966273 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.6556. Min Act: -0.0000

Data Index: 589661 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.8471. Min Act: -0.0000

Data Index: 483459 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.8264. Min Act: -0.0000

Data Index: 383997 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.6560. Min Act: -0.0000

Data Index: 1039329 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.3690. Min Act: -0.0000

Data Index: 491626 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.2711. Min Act: -0.0000

Data Index: 1134133 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.3875. Min Act: -0.0000

Data Index: 234843 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.6040. Min Act: -0.0000

Data Index: 500762 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.3133. Min Act: 0.0001

Data Index: 282437 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.1865. Min Act: -0.0000

Data Index: 38686 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.4963. Min Act: 0.0000

Data Index: 8037 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 4.6127. Min Range: -4.6127

Max Act: 2.3204. Min Act: -0.0000

Data Index: 112558 (C4 (Web Text))

Max Activating Token Index: 473