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

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

Neuron 1724 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.3651. Min Act: -0.0000

Data Index: 114333 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1146888 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.2991. Min Act: -0.0000

Data Index: 870191 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1063826 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1949. Min Act: -0.0000

Data Index: 866696 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1466. Min Act: -0.0000

Data Index: 144802 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1435. Min Act: -0.0000

Data Index: 77641 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1099120 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1597. Min Act: -0.0000

Data Index: 102919 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1323999 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0779. Min Act: -0.0000

Data Index: 722176 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0109. Min Act: -0.0000

Data Index: 843625 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1103583 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0090. Min Act: -0.0000

Data Index: 820448 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.9503. Min Act: 0.0000

Data Index: 980004 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0288. Min Act: -0.0000

Data Index: 590943 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0401. Min Act: -0.0000

Data Index: 99498 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.9607. Min Act: -0.0000

Data Index: 267600 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0177. Min Act: -0.0000

Data Index: 404044 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1186128 (C4 (Web Text))

Max Activating Token Index: 89