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

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

Neuron 2791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5540. Min Range: -2.5540

Max Act: 2.5540. Min Act: -0.0000

Data Index: 1054962 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 2.5540. Min Range: -2.5540

Max Act: 2.0547. Min Act: -0.0000

Data Index: 208429 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.7508. Min Act: -0.0000

Data Index: 420651 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.7394. Min Act: -0.0000

Data Index: 1168525 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.6523. Min Act: -0.0000

Data Index: 472080 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1333719 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.6960. Min Act: -0.0000

Data Index: 215426 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.4945. Min Act: -0.0000

Data Index: 311734 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.5353. Min Act: -0.0000

Data Index: 1126005 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.5589. Min Act: -0.0000

Data Index: 363333 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.4996. Min Act: -0.0000

Data Index: 1034707 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.4900. Min Act: -0.0000

Data Index: 116766 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.4925. Min Act: -0.0000

Data Index: 1308091 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.5706. Min Act: -0.0000

Data Index: 254328 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1081607 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.3954. Min Act: -0.0000

Data Index: 177554 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.4151. Min Act: -0.0000

Data Index: 93468 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.2839. Min Act: -0.0000

Data Index: 677728 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1301665 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.4227. Min Act: -0.0000

Data Index: 116145 (C4 (Web Text))

Max Activating Token Index: 939