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

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

Neuron 585 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: 0.7873. Min Range: -0.7873

Max Act: 0.7873. Min Act: -0.0002

Data Index: 525760 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7792. Min Act: -0.0003

Data Index: 863808 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7809. Min Act: -0.0002

Data Index: 229767 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7745. Min Act: -0.0002

Data Index: 819033 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7525. Min Act: -0.0002

Data Index: 280166 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7588. Min Act: -0.0002

Data Index: 1037616 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7550. Min Act: -0.0002

Data Index: 354569 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7393. Min Act: -0.0002

Data Index: 526919 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7394. Min Act: -0.0002

Data Index: 1208870 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7006. Min Act: -0.0002

Data Index: 478547 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6934. Min Act: -0.0002

Data Index: 933713 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7040. Min Act: -0.0002

Data Index: 1100979 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7113. Min Act: -0.0002

Data Index: 1192641 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6853. Min Act: -0.0002

Data Index: 127916 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6977. Min Act: -0.0002

Data Index: 487684 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6991. Min Act: -0.0002

Data Index: 841883 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6826. Min Act: -0.0002

Data Index: 115262 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6964. Min Act: -0.0002

Data Index: 1197733 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6880. Min Act: -0.0002

Data Index: 645026 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7001. Min Act: -0.0002

Data Index: 32764 (C4 (Web Text))

Max Activating Token Index: 267