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

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

Neuron 852 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: 0.0926. Min Range: -0.0926

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1055293 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0926. Min Act: -0.0002

Data Index: 78379 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0921. Min Act: -0.0002

Data Index: 377722 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1382947 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0895. Min Act: -0.0002

Data Index: 827248 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0890. Min Act: -0.0002

Data Index: 765555 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1211554 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0862. Min Act: -0.0002

Data Index: 150465 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1158656 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0855. Min Act: -0.0002

Data Index: 896054 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0866. Min Act: -0.0002

Data Index: 986413 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1083071 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0853. Min Act: -0.0002

Data Index: 929520 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1303675 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0845. Min Act: -0.0002

Data Index: 835919 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0832. Min Act: -0.0002

Data Index: 802329 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1095964 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0813. Min Act: -0.0002

Data Index: 510793 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0830. Min Act: -0.0002

Data Index: 576432 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1569403 (Python Code)

Max Activating Token Index: 50