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

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

Neuron 2241 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: 2.5686. Min Range: -2.5686

Max Act: 2.5686. Min Act: -0.0000

Data Index: 337260 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 2.5686. Min Range: -2.5686

Max Act: 2.5134. Min Act: -0.0000

Data Index: 405927 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 2.5686. Min Range: -2.5686

Max Act: 2.2345. Min Act: -0.0000

Data Index: 1312351 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 2.5686. Min Range: -2.5686

Max Act: 2.1629. Min Act: -0.0000

Data Index: 1212344 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 2.5686. Min Range: -2.5686

Max Act: 2.1429. Min Act: -0.0000

Data Index: 46601 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.9652. Min Act: -0.0000

Data Index: 1123448 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.9240. Min Act: -0.0000

Data Index: 588771 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 2.5686. Min Range: -2.5686

Max Act: 2.0638. Min Act: -0.0000

Data Index: 69172 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.9667. Min Act: -0.0000

Data Index: 954955 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 2.5686. Min Range: -2.5686

Max Act: 2.1029. Min Act: -0.0000

Data Index: 509317 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 2.5686. Min Range: -2.5686

Max Act: 2.0573. Min Act: -0.0000

Data Index: 824036 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.8922. Min Act: -0.0000

Data Index: 102327 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.9560. Min Act: -0.0000

Data Index: 81249 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 2.5686. Min Range: -2.5686

Max Act: 2.0524. Min Act: -0.0000

Data Index: 38982 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.8989. Min Act: -0.0000

Data Index: 448207 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.8824. Min Act: -0.0000

Data Index: 1131758 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.8722. Min Act: -0.0000

Data Index: 807441 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.8256. Min Act: -0.0000

Data Index: 1313012 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.8577. Min Act: -0.0000

Data Index: 1105773 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 2.5686. Min Range: -2.5686

Max Act: 1.8344. Min Act: -0.0000

Data Index: 84388 (C4 (Web Text))

Max Activating Token Index: 497