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

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

Neuron 2039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.6852. Min Act: -0.0000

Data Index: 965819 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5388. Min Act: -0.0000

Data Index: 234045 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.2008. Min Act: -0.0000

Data Index: 332289 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4071. Min Act: -0.0000

Data Index: 1315576 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.0174. Min Act: -0.0000

Data Index: 891242 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.1395. Min Act: -0.0000

Data Index: 1263935 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.0982. Min Act: -0.0000

Data Index: 1019715 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.2284. Min Act: -0.0000

Data Index: 151287 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.0566. Min Act: -0.0000

Data Index: 796007 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.0366. Min Act: -0.0000

Data Index: 625459 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.8384. Min Act: -0.0000

Data Index: 616874 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.9550. Min Act: -0.0000

Data Index: 410091 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.9343. Min Act: -0.0000

Data Index: 905203 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.0536. Min Act: -0.0000

Data Index: 383673 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.8762. Min Act: -0.0000

Data Index: 731415 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.7944. Min Act: -0.0000

Data Index: 721802 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.7552. Min Act: -0.0000

Data Index: 940672 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.8603. Min Act: -0.0000

Data Index: 671582 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.7089. Min Act: -0.0000

Data Index: 243835 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 3.6852. Min Range: -3.6852

Max Act: 2.5424. Min Act: -0.0000

Data Index: 539720 (C4 (Web Text))

Max Activating Token Index: 308