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

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

Neuron 4787 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.8009. Min Act: -0.0000

Data Index: 337460 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.8265. Min Act: -0.0000

Data Index: 805836 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.9124. Min Act: -0.0000

Data Index: 330606 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6523. Min Act: -0.0000

Data Index: 868917 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.7342. Min Act: -0.0000

Data Index: 969471 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6973. Min Act: -0.0000

Data Index: 1096478 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6325. Min Act: -0.0000

Data Index: 175015 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5536. Min Act: -0.0000

Data Index: 230100 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5523. Min Act: -0.0000

Data Index: 1124908 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5372. Min Act: -0.0000

Data Index: 1230880 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5337. Min Act: -0.0000

Data Index: 787238 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5134. Min Act: -0.0000

Data Index: 293945 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.4256. Min Act: -0.0000

Data Index: 618101 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.4187. Min Act: -0.0000

Data Index: 38514 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.4004. Min Act: -0.0000

Data Index: 759387 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.4022. Min Act: -0.0000

Data Index: 905805 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.4844. Min Act: -0.0000

Data Index: 38093 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.4674. Min Act: -0.0000

Data Index: 629343 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5337. Min Act: -0.0000

Data Index: 974990 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5396. Min Act: -0.0000

Data Index: 696789 (C4 (Web Text))

Max Activating Token Index: 805