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

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

Neuron 3076 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: 1.7017. Min Range: -1.7017

Max Act: 1.7017. Min Act: -0.0000

Data Index: 1348433 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.4607. Min Act: -0.0000

Data Index: 912906 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.4861. Min Act: -0.0000

Data Index: 180943 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.4375. Min Act: -0.0001

Data Index: 99833 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.3926. Min Act: -0.0000

Data Index: 11796 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1126355 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1177834 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2688. Min Act: -0.0000

Data Index: 766601 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1169206 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2550. Min Act: -0.0000

Data Index: 901510 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1304714 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.3490. Min Act: -0.0000

Data Index: 460909 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2734. Min Act: -0.0000

Data Index: 855649 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2975. Min Act: -0.0000

Data Index: 1122960 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2840. Min Act: -0.0000

Data Index: 313914 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2798. Min Act: -0.0000

Data Index: 397451 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2411. Min Act: -0.0000

Data Index: 755403 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2725. Min Act: -0.0000

Data Index: 239900 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2593. Min Act: -0.0001

Data Index: 1049298 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 1.7017. Min Range: -1.7017

Max Act: 1.2510. Min Act: -0.0001

Data Index: 1191599 (C4 (Web Text))

Max Activating Token Index: 556