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

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

Neuron 666 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: 1.4178. Min Range: -1.4178

Max Act: 1.4178. Min Act: -0.0003

Data Index: 1240252 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2732. Min Act: -0.0003

Data Index: 593655 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1664. Min Act: -0.0003

Data Index: 1123222 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0761. Min Act: -0.0003

Data Index: 707523 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0086. Min Act: -0.0003

Data Index: 1017628 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1319. Min Act: -0.0003

Data Index: 628098 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0612. Min Act: -0.0003

Data Index: 550645 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0966. Min Act: -0.0003

Data Index: 1066130 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0539. Min Act: -0.0003

Data Index: 489665 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0522. Min Act: -0.0003

Data Index: 720454 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0248. Min Act: -0.0003

Data Index: 154633 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0729. Min Act: -0.0003

Data Index: 1307299 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0363. Min Act: -0.0003

Data Index: 38311 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.8800. Min Act: -0.0003

Data Index: 195838 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.8972. Min Act: -0.0003

Data Index: 508596 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9996. Min Act: -0.0003

Data Index: 590134 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0028. Min Act: -0.0003

Data Index: 861609 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9681. Min Act: -0.0003

Data Index: 3447 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9384. Min Act: -0.0003

Data Index: 718524 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.8279. Min Act: -0.0003

Data Index: 1107735 (C4 (Web Text))

Max Activating Token Index: 99