Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1568 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1627. Min Act: -0.0003

Data Index: 1234680 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1659. Min Act: -0.0003

Data Index: 288319 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1554. Min Act: -0.0003

Data Index: 798788 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1503. Min Act: -0.0003

Data Index: 807053 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1564. Min Act: -0.0003

Data Index: 1070139 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1410. Min Act: -0.0003

Data Index: 1099059 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1488. Min Act: -0.0003

Data Index: 400396 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1400. Min Act: -0.0003

Data Index: 854240 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1238. Min Act: -0.0003

Data Index: 668641 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1283. Min Act: -0.0003

Data Index: 896337 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1145. Min Act: -0.0003

Data Index: 917123 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1128. Min Act: -0.0003

Data Index: 637459 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1243. Min Act: -0.0003

Data Index: 1345818 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1270. Min Act: -0.0003

Data Index: 281307 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1105. Min Act: -0.0003

Data Index: 228377 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1056. Min Act: -0.0003

Data Index: 574038 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1153. Min Act: -0.0003

Data Index: 319025 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1151. Min Act: -0.0003

Data Index: 1090872 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1034. Min Act: -0.0003

Data Index: 575495 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1102. Min Act: -0.0003

Data Index: 196487 (C4 (Web Text))

Max Activating Token Index: 702