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

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

Neuron 2520 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: 0.1244. Min Range: -0.1244

Max Act: 0.1244. Min Act: -0.0003

Data Index: 628502 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1091. Min Act: -0.0003

Data Index: 638314 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0982. Min Act: -0.0003

Data Index: 749538 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0984. Min Act: -0.0003

Data Index: 5848 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0937. Min Act: -0.0003

Data Index: 228633 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0994. Min Act: -0.0003

Data Index: 221421 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0931. Min Act: -0.0003

Data Index: 812200 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0905. Min Act: -0.0003

Data Index: 223799 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0786. Min Act: -0.0003

Data Index: 966304 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0890. Min Act: -0.0003

Data Index: 924185 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0864. Min Act: -0.0003

Data Index: 207880 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0841. Min Act: -0.0003

Data Index: 272736 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0811. Min Act: -0.0003

Data Index: 534520 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0776. Min Act: -0.0003

Data Index: 1204662 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0762. Min Act: -0.0003

Data Index: 851655 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0868. Min Act: -0.0003

Data Index: 766169 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0836. Min Act: -0.0003

Data Index: 528121 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1249215 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0692. Min Act: -0.0003

Data Index: 559355 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0767. Min Act: -0.0003

Data Index: 517692 (C4 (Web Text))

Max Activating Token Index: 920