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

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

Neuron 5453 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0254. Min Range: -3.0254

Max Act: 3.0254. Min Act: -0.0000

Data Index: 1477770 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.9559. Min Act: -0.0000

Data Index: 1495468 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.8720. Min Act: -0.0000

Data Index: 563638 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.8563. Min Act: -0.0000

Data Index: 962596 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.7785. Min Act: -0.0000

Data Index: 983700 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.8422. Min Act: -0.0000

Data Index: 1611072 (Python Code)

Max Activating Token Index: 856

Text #6

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.6495. Min Act: -0.0000

Data Index: 986221 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.5560. Min Act: -0.0000

Data Index: 1048714 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.6919. Min Act: -0.0000

Data Index: 232771 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.4147. Min Act: -0.0000

Data Index: 890478 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.5328. Min Act: -0.0000

Data Index: 345068 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.3896. Min Act: -0.0000

Data Index: 306673 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.4966. Min Act: -0.0000

Data Index: 1526390 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.4807. Min Act: -0.0000

Data Index: 384756 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.4184. Min Act: -0.0000

Data Index: 1168030 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.4125. Min Act: -0.0000

Data Index: 21192 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.4244. Min Act: -0.0000

Data Index: 172783 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.2884. Min Act: -0.0000

Data Index: 1607220 (Python Code)

Max Activating Token Index: 911

Text #18

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.3893. Min Act: -0.0000

Data Index: 405135 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 3.0254. Min Range: -3.0254

Max Act: 2.3872. Min Act: -0.0000

Data Index: 273686 (C4 (Web Text))

Max Activating Token Index: 41