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

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

Neuron 1234 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: 1.7368. Min Range: -1.7368

Max Act: 1.7368. Min Act: -0.0002

Data Index: 627787 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.7140. Min Act: -0.0002

Data Index: 254896 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.7123. Min Act: -0.0002

Data Index: 541001 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6653. Min Act: -0.0002

Data Index: 458047 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6247. Min Act: -0.0002

Data Index: 492381 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6780. Min Act: -0.0002

Data Index: 604379 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6826. Min Act: -0.0002

Data Index: 568077 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6493. Min Act: -0.0002

Data Index: 1334573 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6406. Min Act: -0.0002

Data Index: 1047884 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6079. Min Act: -0.0002

Data Index: 1239584 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5464. Min Act: -0.0002

Data Index: 95909 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5470. Min Act: -0.0002

Data Index: 1359403 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5713. Min Act: -0.0002

Data Index: 904496 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5634. Min Act: -0.0002

Data Index: 1052895 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6016. Min Act: -0.0002

Data Index: 278600 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5473. Min Act: -0.0002

Data Index: 1051632 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6164. Min Act: -0.0002

Data Index: 621566 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5500. Min Act: -0.0002

Data Index: 1079524 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5899. Min Act: -0.0002

Data Index: 1231418 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5434. Min Act: -0.0002

Data Index: 1291657 (C4 (Web Text))

Max Activating Token Index: 112