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

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

Neuron 1561 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.7759. Min Act: -0.0001

Data Index: 939787 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.0570. Min Range: -3.0570

Max Act: 3.0570. Min Act: -0.0001

Data Index: 258275 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.9085. Min Act: -0.0002

Data Index: 305150 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.6469. Min Act: -0.0002

Data Index: 182929 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.4998. Min Act: -0.0002

Data Index: 526980 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.1973. Min Act: -0.0001

Data Index: 324552 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.3536. Min Act: -0.0002

Data Index: 656172 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.5683. Min Act: -0.0002

Data Index: 764482 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 3.0570. Min Range: -3.0570

Max Act: 1.9958. Min Act: -0.0002

Data Index: 1238665 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.1926. Min Act: -0.0002

Data Index: 1198352 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.0542. Min Act: -0.0002

Data Index: 110035 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.1446. Min Act: -0.0002

Data Index: 404957 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.0765. Min Act: -0.0002

Data Index: 671077 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 3.0570. Min Range: -3.0570

Max Act: 1.9720. Min Act: -0.0001

Data Index: 250585 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.0570. Min Range: -3.0570

Max Act: 1.9241. Min Act: -0.0001

Data Index: 860136 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 3.0570. Min Range: -3.0570

Max Act: 1.9084. Min Act: -0.0001

Data Index: 344080 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 3.0570. Min Range: -3.0570

Max Act: 1.9100. Min Act: -0.0002

Data Index: 1096843 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 3.0570. Min Range: -3.0570

Max Act: 2.1559. Min Act: -0.0001

Data Index: 441866 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 3.0570. Min Range: -3.0570

Max Act: 1.8386. Min Act: -0.0002

Data Index: 659368 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 3.0570. Min Range: -3.0570

Max Act: 1.8305. Min Act: -0.0002

Data Index: 73760 (C4 (Web Text))

Max Activating Token Index: 475