Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1826 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0865. Min Act: -0.0001

Data Index: 322776 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.1459. Min Act: -0.0001

Data Index: 1126372 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0938. Min Act: -0.0001

Data Index: 88762 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.1426. Min Act: -0.0001

Data Index: 1147954 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0329. Min Act: -0.0001

Data Index: 504626 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0486. Min Act: -0.0001

Data Index: 1025497 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.1457. Min Act: -0.0001

Data Index: 683010 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0568. Min Act: -0.0001

Data Index: 185972 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9737. Min Act: -0.0001

Data Index: 1193078 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9506. Min Act: -0.0001

Data Index: 333114 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0033. Min Act: -0.0001

Data Index: 1325862 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9228. Min Act: -0.0001

Data Index: 922023 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0107. Min Act: -0.0001

Data Index: 801542 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.8080. Min Act: -0.0001

Data Index: 568002 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9879. Min Act: -0.0001

Data Index: 430421 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9008. Min Act: -0.0001

Data Index: 1198559 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9362. Min Act: -0.0001

Data Index: 732231 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.8739. Min Act: -0.0001

Data Index: 181092 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1242742 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1093338 (C4 (Web Text))

Max Activating Token Index: 725