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

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

Neuron 638 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: 1.8304. Min Range: -1.8304

Max Act: 1.8304. Min Act: -0.0002

Data Index: 1019668 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.8304. Min Act: -0.0002

Data Index: 414589 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.8304. Min Act: -0.0002

Data Index: 596071 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.7305. Min Act: -0.0002

Data Index: 186946 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.7231. Min Act: -0.0002

Data Index: 1313231 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.7683. Min Act: -0.0002

Data Index: 779934 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6567. Min Act: -0.0002

Data Index: 80636 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6569. Min Act: -0.0002

Data Index: 451722 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6381. Min Act: -0.0002

Data Index: 909044 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6381. Min Act: -0.0002

Data Index: 775889 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6381. Min Act: -0.0002

Data Index: 608553 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6711. Min Act: -0.0002

Data Index: 984317 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6176. Min Act: -0.0002

Data Index: 293637 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6620. Min Act: -0.0002

Data Index: 511454 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6363. Min Act: -0.0002

Data Index: 866328 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6102. Min Act: -0.0003

Data Index: 1210579 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6620. Min Act: -0.0002

Data Index: 1127528 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6045. Min Act: -0.0002

Data Index: 1147952 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6028. Min Act: -0.0002

Data Index: 215912 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 1.8304. Min Range: -1.8304

Max Act: 1.6018. Min Act: -0.0002

Data Index: 488383 (C4 (Web Text))

Max Activating Token Index: 8