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

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

Neuron 1190 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: 0.2070. Min Range: -0.2070

Max Act: 0.2070. Min Act: -0.0000

Data Index: 11524 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1262993 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1927. Min Act: -0.0000

Data Index: 17379 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1159616 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1739. Min Act: -0.0000

Data Index: 468197 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1784. Min Act: -0.0000

Data Index: 360013 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1334251 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1727. Min Act: -0.0000

Data Index: 499051 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1665. Min Act: -0.0000

Data Index: 911302 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1480. Min Act: -0.0000

Data Index: 603417 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1273738 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1474. Min Act: -0.0000

Data Index: 160551 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1499. Min Act: 0.0000

Data Index: 889799 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1395. Min Act: -0.0000

Data Index: 739546 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1392. Min Act: -0.0000

Data Index: 928424 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1340. Min Act: -0.0000

Data Index: 317108 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1054084 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1288. Min Act: -0.0000

Data Index: 464146 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1114333 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1164203 (C4 (Web Text))

Max Activating Token Index: 303