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

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

Neuron 2311 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6743. Min Act: -0.0000

Data Index: 707614 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5003. Min Act: -0.0000

Data Index: 71744 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4979. Min Act: -0.0000

Data Index: 818263 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1150395 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1126374 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4560. Min Act: -0.0000

Data Index: 169786 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1009833 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4611. Min Act: -0.0000

Data Index: 745626 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4753. Min Act: -0.0000

Data Index: 775967 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1324621 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4529. Min Act: -0.0000

Data Index: 79448 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1197353 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4551. Min Act: -0.0000

Data Index: 814388 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4370. Min Act: -0.0000

Data Index: 385646 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4538. Min Act: -0.0000

Data Index: 769301 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4486. Min Act: -0.0000

Data Index: 843716 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1310056 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4277. Min Act: -0.0000

Data Index: 147817 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1145321 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4168. Min Act: -0.0000

Data Index: 224817 (C4 (Web Text))

Max Activating Token Index: 239