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

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

Neuron 3818 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.9511. Min Act: -0.0000

Data Index: 813460 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.8881. Min Act: -0.0000

Data Index: 613016 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.8226. Min Act: -0.0000

Data Index: 89005 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.8097. Min Act: -0.0000

Data Index: 633838 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.8085. Min Act: -0.0001

Data Index: 292105 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.8558. Min Act: -0.0001

Data Index: 301832 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.8186. Min Act: -0.0000

Data Index: 596309 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7701. Min Act: -0.0001

Data Index: 357789 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.8067. Min Act: -0.0000

Data Index: 522875 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1208184 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7438. Min Act: -0.0001

Data Index: 69404 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7851. Min Act: -0.0001

Data Index: 669894 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7500. Min Act: -0.0001

Data Index: 1276764 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7650. Min Act: -0.0000

Data Index: 169062 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.6982. Min Act: -0.0000

Data Index: 773246 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7394. Min Act: -0.0000

Data Index: 937963 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7285. Min Act: -0.0000

Data Index: 105994 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7240. Min Act: -0.0000

Data Index: 698728 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7073. Min Act: -0.0000

Data Index: 576300 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.9511. Min Range: -0.9511

Max Act: 0.7053. Min Act: -0.0000

Data Index: 234991 (C4 (Web Text))

Max Activating Token Index: 343