Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3502 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.8837. Min Act: -0.0000

Data Index: 198608 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7830. Min Act: -0.0001

Data Index: 702591 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7340. Min Act: -0.0000

Data Index: 670327 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6723. Min Act: -0.0000

Data Index: 892036 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6866. Min Act: -0.0001

Data Index: 410799 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6564. Min Act: -0.0000

Data Index: 311124 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6159. Min Act: -0.0001

Data Index: 99155 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1148648 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5428. Min Act: -0.0001

Data Index: 845933 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5067. Min Act: -0.0000

Data Index: 753307 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5198. Min Act: -0.0001

Data Index: 248784 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4906. Min Act: -0.0001

Data Index: 1172354 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5048. Min Act: -0.0000

Data Index: 382699 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4881. Min Act: -0.0000

Data Index: 587009 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4265. Min Act: -0.0000

Data Index: 602452 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4668. Min Act: -0.0001

Data Index: 218352 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4654. Min Act: -0.0000

Data Index: 512303 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4523. Min Act: -0.0001

Data Index: 887003 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4621. Min Act: -0.0000

Data Index: 781785 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4586. Min Act: -0.0001

Data Index: 530447 (C4 (Web Text))

Max Activating Token Index: 933