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

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

Neuron 755 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1235118 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.5757. Min Act: -0.0001

Data Index: 893045 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.5712. Min Act: -0.0001

Data Index: 61617 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4732. Min Act: -0.0000

Data Index: 558919 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.5064. Min Act: -0.0001

Data Index: 75513 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4832. Min Act: -0.0000

Data Index: 623227 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4483. Min Act: -0.0001

Data Index: 1243752 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4841. Min Act: -0.0001

Data Index: 978611 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4622. Min Act: -0.0001

Data Index: 351283 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4945. Min Act: -0.0000

Data Index: 730632 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4373. Min Act: -0.0001

Data Index: 969697 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4364. Min Act: -0.0001

Data Index: 379648 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4403. Min Act: -0.0001

Data Index: 108377 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4387. Min Act: -0.0000

Data Index: 142321 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4511. Min Act: -0.0001

Data Index: 1032620 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4342. Min Act: -0.0000

Data Index: 38698 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4395. Min Act: -0.0001

Data Index: 108731 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4517. Min Act: -0.0001

Data Index: 960944 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4236. Min Act: -0.0001

Data Index: 136869 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4183. Min Act: -0.0000

Data Index: 487632 (C4 (Web Text))

Max Activating Token Index: 849