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

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

Neuron 5006 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8441. Min Act: -0.0001

Data Index: 690574 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1149195 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8979. Min Act: -0.0001

Data Index: 185988 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1186759 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7807. Min Act: -0.0001

Data Index: 1038280 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7476. Min Act: -0.0000

Data Index: 490809 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1206452 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7479. Min Act: -0.0000

Data Index: 385122 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7276. Min Act: -0.0001

Data Index: 1305601 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6784. Min Act: -0.0001

Data Index: 258666 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7037. Min Act: -0.0000

Data Index: 954516 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1140352 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6506. Min Act: -0.0000

Data Index: 585348 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6833. Min Act: -0.0000

Data Index: 787526 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1302254 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6694. Min Act: -0.0001

Data Index: 180742 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6409. Min Act: -0.0001

Data Index: 79906 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6392. Min Act: -0.0000

Data Index: 445775 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6903. Min Act: -0.0000

Data Index: 2471 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6207. Min Act: -0.0000

Data Index: 882608 (C4 (Web Text))

Max Activating Token Index: 554