Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4770 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.5790. Min Act: -0.0000

Data Index: 292854 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.4374. Min Act: -0.0000

Data Index: 604890 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3825. Min Act: -0.0000

Data Index: 87761 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.4008. Min Act: -0.0000

Data Index: 138748 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1074906 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3631. Min Act: -0.0000

Data Index: 843590 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3470. Min Act: -0.0000

Data Index: 146819 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1118447 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3705. Min Act: -0.0000

Data Index: 721720 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3557. Min Act: -0.0000

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3470. Min Act: -0.0000

Data Index: 526897 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1252504 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3253. Min Act: -0.0000

Data Index: 299003 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3270. Min Act: -0.0000

Data Index: 773239 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2928. Min Act: -0.0000

Data Index: 565699 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1092791 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2682. Min Act: -0.0000

Data Index: 24878 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1044303 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2872. Min Act: -0.0000

Data Index: 618718 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2925. Min Act: -0.0000

Data Index: 398409 (C4 (Web Text))

Max Activating Token Index: 107