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

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

Neuron 1814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5877. Min Act: -0.0001

Data Index: 490599 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5405. Min Act: -0.0000

Data Index: 856175 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5640. Min Act: -0.0000

Data Index: 811397 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5013. Min Act: -0.0001

Data Index: 747166 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1297770 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5004. Min Act: -0.0000

Data Index: 345123 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1198089 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5246. Min Act: -0.0001

Data Index: 3133 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5062. Min Act: -0.0000

Data Index: 714484 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1171953 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4721. Min Act: -0.0000

Data Index: 146927 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4549. Min Act: -0.0000

Data Index: 975910 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4832. Min Act: -0.0001

Data Index: 730949 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4626. Min Act: -0.0001

Data Index: 894052 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4566. Min Act: -0.0000

Data Index: 86558 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4501. Min Act: -0.0000

Data Index: 616537 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4513. Min Act: -0.0000

Data Index: 525797 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4642. Min Act: -0.0000

Data Index: 623100 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4463. Min Act: -0.0000

Data Index: 527479 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4185. Min Act: -0.0000

Data Index: 531237 (C4 (Web Text))

Max Activating Token Index: 705