Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.6086. Min Act: -0.0000

Data Index: 146222 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.5024. Min Act: -0.0000

Data Index: 1114579 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.4582. Min Act: -0.0000

Data Index: 321097 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.3438. Min Act: -0.0000

Data Index: 577598 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.2520. Min Act: -0.0000

Data Index: 941939 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.2334. Min Act: -0.0000

Data Index: 176948 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.2237. Min Act: -0.0000

Data Index: 593157 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.1612. Min Act: -0.0000

Data Index: 956475 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.2289. Min Act: -0.0000

Data Index: 605761 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.1266. Min Act: -0.0000

Data Index: 17635 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.1037. Min Act: -0.0000

Data Index: 158562 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.0760. Min Act: -0.0000

Data Index: 241835 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.1692. Min Act: -0.0000

Data Index: 895154 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.0837. Min Act: -0.0000

Data Index: 277460 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.1488. Min Act: -0.0000

Data Index: 44834 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.0229. Min Act: -0.0000

Data Index: 675064 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.0752. Min Act: -0.0000

Data Index: 861203 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.6086. Min Range: -1.6086

Max Act: 0.9974. Min Act: -0.0000

Data Index: 268570 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 1.6086. Min Range: -1.6086

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1232344 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.6086. Min Range: -1.6086

Max Act: 0.9987. Min Act: -0.0000

Data Index: 695231 (C4 (Web Text))

Max Activating Token Index: 658