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

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

Neuron 3200 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: 0.5915. Min Range: -0.5915

Max Act: 0.5915. Min Act: -0.0000

Data Index: 128669 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.5500. Min Act: -0.0000

Data Index: 78660 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.5204. Min Act: -0.0000

Data Index: 351051 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.5164. Min Act: -0.0000

Data Index: 114152 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.5054. Min Act: -0.0000

Data Index: 308054 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.5098. Min Act: -0.0000

Data Index: 66337 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.5057. Min Act: -0.0000

Data Index: 174008 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.4470. Min Act: -0.0000

Data Index: 599721 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.4356. Min Act: -0.0000

Data Index: 942156 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.4412. Min Act: -0.0000

Data Index: 452253 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.4351. Min Act: -0.0000

Data Index: 162764 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.4204. Min Act: -0.0000

Data Index: 108850 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1047118 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.4312. Min Act: -0.0000

Data Index: 722469 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.3854. Min Act: -0.0000

Data Index: 24496 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.3918. Min Act: -0.0000

Data Index: 22786 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1035052 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.3870. Min Act: -0.0000

Data Index: 248213 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1216757 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.5915. Min Range: -0.5915

Max Act: 0.3962. Min Act: -0.0000

Data Index: 755316 (C4 (Web Text))

Max Activating Token Index: 268