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

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

Neuron 17 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.5847. Min Act: -0.0000

Data Index: 234707 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.4381. Min Act: -0.0000

Data Index: 267872 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.5351. Min Act: -0.0000

Data Index: 456275 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.2660. Min Act: -0.0000

Data Index: 749543 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.1161. Min Act: -0.0000

Data Index: 697159 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.2016. Min Act: -0.0000

Data Index: 949772 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.9889. Min Act: -0.0000

Data Index: 74237 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.0592. Min Act: -0.0000

Data Index: 367427 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.1353. Min Act: -0.0000

Data Index: 855697 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.0187. Min Act: -0.0000

Data Index: 319877 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.0014. Min Act: -0.0000

Data Index: 753775 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.9733. Min Act: -0.0000

Data Index: 8591 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.0413. Min Act: -0.0000

Data Index: 360459 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.9403. Min Act: -0.0000

Data Index: 819076 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.9811. Min Act: -0.0000

Data Index: 1026121 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.7873. Min Act: -0.0000

Data Index: 597723 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.8738. Min Act: -0.0000

Data Index: 643283 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.8696. Min Act: -0.0000

Data Index: 1116858 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.8653. Min Act: -0.0000

Data Index: 789584 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.9598. Min Act: -0.0000

Data Index: 22686 (C4 (Web Text))

Max Activating Token Index: 111