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

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

Neuron 2941 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5721. Min Act: -0.0001

Data Index: 851426 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.6008. Min Act: -0.0001

Data Index: 1215855 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5612. Min Act: -0.0001

Data Index: 798571 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5651. Min Act: -0.0001

Data Index: 521250 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5414. Min Act: -0.0001

Data Index: 955795 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5447. Min Act: -0.0001

Data Index: 1573655 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5616. Min Act: -0.0001

Data Index: 1130261 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5588. Min Act: -0.0001

Data Index: 453417 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1272307 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5276. Min Act: -0.0001

Data Index: 810459 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5253. Min Act: -0.0001

Data Index: 740053 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5251. Min Act: -0.0001

Data Index: 241593 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5386. Min Act: -0.0001

Data Index: 92489 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5013. Min Act: -0.0001

Data Index: 13452 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5176. Min Act: -0.0001

Data Index: 470612 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4959. Min Act: -0.0001

Data Index: 1233027 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5113. Min Act: -0.0001

Data Index: 1010330 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5278. Min Act: -0.0001

Data Index: 155252 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5053. Min Act: -0.0001

Data Index: 597196 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5027. Min Act: -0.0001

Data Index: 172100 (C4 (Web Text))

Max Activating Token Index: 356