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

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

Neuron 2556 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.3581. Min Act: -0.0000

Data Index: 733873 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.9705. Min Act: -0.0000

Data Index: 366088 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.0364. Min Act: -0.0000

Data Index: 259213 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.9030. Min Act: -0.0000

Data Index: 683879 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.7796. Min Act: -0.0000

Data Index: 7521 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1097737 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.6843. Min Act: -0.0000

Data Index: 715408 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1065 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.6304. Min Act: -0.0000

Data Index: 813238 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.5546. Min Act: -0.0000

Data Index: 412053 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1081040 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1207424 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.5979. Min Act: -0.0000

Data Index: 87347 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.6060. Min Act: -0.0000

Data Index: 6822 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1013364 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.5872. Min Act: -0.0000

Data Index: 670065 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.5515. Min Act: -0.0000

Data Index: 162037 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.5592. Min Act: -0.0000

Data Index: 26137 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.4673. Min Act: -0.0000

Data Index: 727653 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1162629 (C4 (Web Text))

Max Activating Token Index: 21