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

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

Neuron 4673 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: 1.3562. Min Range: -1.3562

Max Act: 1.3387. Min Act: -0.0000

Data Index: 172585 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.3562. Min Act: -0.0000

Data Index: 453865 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.2628. Min Act: -0.0000

Data Index: 442904 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.2210. Min Act: -0.0000

Data Index: 368510 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.2167. Min Act: -0.0000

Data Index: 962989 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.1933. Min Act: -0.0000

Data Index: 24509 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.1613. Min Act: -0.0000

Data Index: 281395 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.1569. Min Act: -0.0000

Data Index: 428135 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1259219 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1028695 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.1149. Min Act: -0.0000

Data Index: 290480 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.1079. Min Act: -0.0000

Data Index: 414885 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1289520 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.1097. Min Act: -0.0000

Data Index: 178566 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.0944. Min Act: -0.0000

Data Index: 136701 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.0890. Min Act: -0.0000

Data Index: 156008 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.0575. Min Act: -0.0000

Data Index: 6089 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.0163. Min Act: -0.0000

Data Index: 690914 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.0550. Min Act: -0.0000

Data Index: 376294 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.3562. Min Range: -1.3562

Max Act: 1.0550. Min Act: -0.0000

Data Index: 232894 (C4 (Web Text))

Max Activating Token Index: 972