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

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

Neuron 492 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: 1.3390. Min Range: -1.3390

Max Act: 1.3390. Min Act: -0.0000

Data Index: 765456 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1252229 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1472. Min Act: -0.0000

Data Index: 315158 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1379. Min Act: -0.0000

Data Index: 367188 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1349. Min Act: -0.0000

Data Index: 907310 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9865. Min Act: -0.0000

Data Index: 929420 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9844. Min Act: -0.0000

Data Index: 780835 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8947. Min Act: -0.0000

Data Index: 390288 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8745. Min Act: -0.0000

Data Index: 264166 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.7941. Min Act: -0.0000

Data Index: 801310 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8554. Min Act: -0.0000

Data Index: 20147 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8629. Min Act: -0.0000

Data Index: 39506 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1279999 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1194120 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1024711 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.7862. Min Act: -0.0000

Data Index: 171183 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1097904 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.7535. Min Act: -0.0000

Data Index: 914713 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.7431. Min Act: -0.0000

Data Index: 165365 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.7712. Min Act: -0.0000

Data Index: 720581 (C4 (Web Text))

Max Activating Token Index: 742