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

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

Neuron 3919 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.8066. Min Act: -0.0001

Data Index: 1092589 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.8440. Min Act: -0.0001

Data Index: 1003768 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.0357. Min Act: -0.0001

Data Index: 1073484 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.7925. Min Act: -0.0001

Data Index: 1169626 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.7988. Min Act: -0.0001

Data Index: 14882 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.4281. Min Act: -0.0001

Data Index: 1328753 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.5084. Min Act: -0.0001

Data Index: 161742 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.1699. Min Act: -0.0001

Data Index: 151483 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.4487. Min Act: -0.0001

Data Index: 1235609 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.0558. Min Act: -0.0001

Data Index: 644347 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.3079. Min Act: -0.0001

Data Index: 510705 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 5.8066. Min Range: -5.8066

Max Act: 3.7603. Min Act: -0.0001

Data Index: 524552 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.1910. Min Act: -0.0001

Data Index: 110084 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.0214. Min Act: -0.0001

Data Index: 426716 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.1013. Min Act: -0.0001

Data Index: 631371 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 5.8066. Min Range: -5.8066

Max Act: 4.5887. Min Act: -0.0001

Data Index: 149961 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 5.8066. Min Range: -5.8066

Max Act: 3.4414. Min Act: -0.0001

Data Index: 277173 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 5.8066. Min Range: -5.8066

Max Act: 3.9983. Min Act: -0.0001

Data Index: 1337661 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 5.8066. Min Range: -5.8066

Max Act: 3.8854. Min Act: -0.0001

Data Index: 915856 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 5.8066. Min Range: -5.8066

Max Act: 3.7458. Min Act: -0.0001

Data Index: 49757 (C4 (Web Text))

Max Activating Token Index: 300