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

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

Neuron 4757 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: 1.0984. Min Range: -1.0984

Max Act: 1.0984. Min Act: -0.0003

Data Index: 492909 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0441. Min Act: -0.0002

Data Index: 548846 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0303. Min Act: -0.0002

Data Index: 1222563 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0035. Min Act: -0.0002

Data Index: 825622 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9572. Min Act: -0.0002

Data Index: 131423 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8769. Min Act: -0.0002

Data Index: 901672 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8873. Min Act: -0.0002

Data Index: 478690 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8718. Min Act: -0.0002

Data Index: 889145 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8656. Min Act: -0.0002

Data Index: 27023 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8778. Min Act: -0.0002

Data Index: 604034 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8753. Min Act: -0.0002

Data Index: 317605 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8571. Min Act: -0.0002

Data Index: 120588 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8417. Min Act: -0.0002

Data Index: 687557 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8403. Min Act: -0.0002

Data Index: 1147350 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8351. Min Act: -0.0002

Data Index: 1093070 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8452. Min Act: -0.0002

Data Index: 1270751 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8346. Min Act: -0.0002

Data Index: 899361 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8301. Min Act: -0.0002

Data Index: 1028172 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8056. Min Act: -0.0002

Data Index: 401541 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7972. Min Act: -0.0002

Data Index: 732463 (C4 (Web Text))

Max Activating Token Index: 423