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

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

Neuron 2952 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: 0.7190. Min Range: -0.7190

Max Act: 0.7190. Min Act: -0.0000

Data Index: 380559 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.7070. Min Act: -0.0000

Data Index: 876674 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1336510 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1637241 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1362856 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1257570 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1496738 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6177. Min Act: -0.0000

Data Index: 641487 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5976. Min Act: -0.0000

Data Index: 70657 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1025745 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6067. Min Act: -0.0000

Data Index: 956941 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1357073 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5681. Min Act: -0.0000

Data Index: 479540 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1121992 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1328408 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5475. Min Act: -0.0000

Data Index: 425098 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5141. Min Act: -0.0000

Data Index: 961764 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1093600 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5615. Min Act: -0.0001

Data Index: 658561 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5419. Min Act: -0.0000

Data Index: 246182 (C4 (Web Text))

Max Activating Token Index: 1013