Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4269 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4482. Min Act: -0.0000

Data Index: 132037 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.3704. Min Act: -0.0000

Data Index: 1053393 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.5267. Min Act: -0.0000

Data Index: 884255 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.2098. Min Act: -0.0000

Data Index: 555053 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.3016. Min Act: -0.0000

Data Index: 1063084 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.2511. Min Act: -0.0000

Data Index: 185264 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.2407. Min Act: -0.0000

Data Index: 811569 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.2474. Min Act: -0.0000

Data Index: 810013 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.3106. Min Act: -0.0000

Data Index: 1188993 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.1320. Min Act: -0.0000

Data Index: 543349 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 3.5267. Min Range: -3.5267

Max Act: 2.9047. Min Act: -0.0000

Data Index: 611191 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.0493. Min Act: -0.0000

Data Index: 1204997 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 3.5267. Min Range: -3.5267

Max Act: 2.8950. Min Act: -0.0000

Data Index: 95328 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.1799. Min Act: -0.0000

Data Index: 691815 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.1692. Min Act: -0.0000

Data Index: 645679 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.1840. Min Act: -0.0000

Data Index: 219659 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.0246. Min Act: -0.0000

Data Index: 33798 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.5267. Min Range: -3.5267

Max Act: 2.9793. Min Act: -0.0000

Data Index: 596418 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 3.5267. Min Range: -3.5267

Max Act: 2.7140. Min Act: -0.0000

Data Index: 1218142 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.0932. Min Act: -0.0000

Data Index: 1322487 (C4 (Web Text))

Max Activating Token Index: 127