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

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

Neuron 1019 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1166193 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1000352 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1149. Min Act: -0.0001

Data Index: 758144 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1111. Min Act: -0.0001

Data Index: 713069 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1104. Min Act: -0.0001

Data Index: 108203 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1102. Min Act: -0.0001

Data Index: 362760 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1051. Min Act: -0.0001

Data Index: 342910 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1238430 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1208135 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1025. Min Act: -0.0001

Data Index: 763240 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1204971 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0982. Min Act: -0.0001

Data Index: 122101 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1023. Min Act: -0.0001

Data Index: 518663 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0937. Min Act: -0.0001

Data Index: 391296 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0934. Min Act: -0.0001

Data Index: 594431 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0994. Min Act: -0.0001

Data Index: 376428 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1205017 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0962. Min Act: -0.0001

Data Index: 6855 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0925. Min Act: -0.0001

Data Index: 9722 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1255274 (C4 (Web Text))

Max Activating Token Index: 780