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

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

Neuron 3454 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.8672. Min Act: -0.0000

Data Index: 1526935 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.6836. Min Act: -0.0000

Data Index: 544034 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.3040. Min Act: -0.0000

Data Index: 960883 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.1150. Min Act: -0.0000

Data Index: 1175388 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.3953. Min Act: -0.0000

Data Index: 559086 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.5714. Min Act: -0.0000

Data Index: 571962 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.6740. Min Act: -0.0000

Data Index: 379285 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.6746. Min Act: -0.0000

Data Index: 354658 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.1223. Min Act: -0.0000

Data Index: 1321121 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.2925. Min Act: -0.0000

Data Index: 678288 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.2555. Min Act: -0.0000

Data Index: 569683 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.0893. Min Act: -0.0000

Data Index: 1003904 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 5.8672. Min Range: -5.8672

Max Act: 4.8708. Min Act: -0.0000

Data Index: 721886 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.0584. Min Act: -0.0000

Data Index: 110467 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.4059. Min Act: -0.0000

Data Index: 910386 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.2164. Min Act: -0.0000

Data Index: 374276 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.0575. Min Act: -0.0000

Data Index: 179308 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 5.8672. Min Range: -5.8672

Max Act: 4.8618. Min Act: -0.0000

Data Index: 325100 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 5.8672. Min Range: -5.8672

Max Act: 4.8457. Min Act: -0.0000

Data Index: 840374 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 5.8672. Min Range: -5.8672

Max Act: 5.1544. Min Act: -0.0000

Data Index: 601192 (C4 (Web Text))

Max Activating Token Index: 731