Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3946 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1446. Min Range: -3.1446

Max Act: 3.1446. Min Act: -0.0002

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.6654. Min Act: -0.0002

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.6000. Min Act: -0.0002

Data Index: 364664 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.5776. Min Act: -0.0003

Data Index: 760960 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.5885. Min Act: -0.0002

Data Index: 81792 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.5560. Min Act: -0.0002

Data Index: 1211229 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.4749. Min Act: -0.0002

Data Index: 807353 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.4485. Min Act: -0.0002

Data Index: 183434 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.4164. Min Act: -0.0002

Data Index: 1027175 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.4105. Min Act: -0.0002

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.3676. Min Act: -0.0002

Data Index: 1248243 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.4238. Min Act: -0.0002

Data Index: 664560 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.3482. Min Act: -0.0002

Data Index: 475256 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.3470. Min Act: -0.0003

Data Index: 629796 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.3472. Min Act: -0.0002

Data Index: 187731 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.2699. Min Act: -0.0002

Data Index: 773804 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.2571. Min Act: -0.0003

Data Index: 79072 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.2853. Min Act: -0.0002

Data Index: 431766 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.2350. Min Act: -0.0002

Data Index: 460830 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 3.1446. Min Range: -3.1446

Max Act: 2.2117. Min Act: -0.0002

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 406