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

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

Neuron 422 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.4658. Min Act: -0.0003

Data Index: 1063300 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2379. Min Act: -0.0003

Data Index: 12798 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2917. Min Act: -0.0003

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0166. Min Act: -0.0003

Data Index: 878049 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2332. Min Act: -0.0003

Data Index: 773698 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1983. Min Act: -0.0003

Data Index: 540141 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1083. Min Act: -0.0003

Data Index: 310023 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1643. Min Act: -0.0003

Data Index: 1035933 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1963. Min Act: -0.0003

Data Index: 1222181 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0047. Min Act: -0.0003

Data Index: 513216 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0401. Min Act: -0.0003

Data Index: 1338127 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1851. Min Act: -0.0003

Data Index: 884162 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1044. Min Act: -0.0003

Data Index: 335745 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0871. Min Act: -0.0003

Data Index: 243237 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0590. Min Act: -0.0003

Data Index: 951352 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1324. Min Act: -0.0003

Data Index: 76114 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2205. Min Act: -0.0003

Data Index: 749230 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1850. Min Act: -0.0003

Data Index: 232837 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1472. Min Act: -0.0003

Data Index: 872291 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1448. Min Act: -0.0003

Data Index: 779489 (C4 (Web Text))

Max Activating Token Index: 112