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

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

Neuron 5319 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: 1.4393. Min Range: -1.4393

Max Act: 1.4393. Min Act: -0.0002

Data Index: 591686 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.4393. Min Act: -0.0002

Data Index: 483113 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.3537. Min Act: -0.0002

Data Index: 226812 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2937. Min Act: -0.0002

Data Index: 372103 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2215. Min Act: -0.0002

Data Index: 659857 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2004. Min Act: -0.0002

Data Index: 358287 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1906. Min Act: -0.0002

Data Index: 772511 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1581. Min Act: -0.0003

Data Index: 561916 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1628. Min Act: -0.0002

Data Index: 672963 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1632. Min Act: -0.0002

Data Index: 1317128 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1518. Min Act: -0.0002

Data Index: 1278439 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1326. Min Act: -0.0002

Data Index: 1098086 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1062. Min Act: -0.0002

Data Index: 16488 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1025. Min Act: -0.0002

Data Index: 74759 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0763. Min Act: -0.0002

Data Index: 934976 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0777. Min Act: -0.0002

Data Index: 730414 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0879. Min Act: -0.0002

Data Index: 235919 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0740. Min Act: -0.0002

Data Index: 913470 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0525. Min Act: -0.0002

Data Index: 120617 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0514. Min Act: -0.0002

Data Index: 575229 (C4 (Web Text))

Max Activating Token Index: 15