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

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

Neuron 769 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.8928. Min Act: -0.0000

Data Index: 1102653 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.8056. Min Act: -0.0000

Data Index: 266462 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7495. Min Act: -0.0000

Data Index: 343666 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7049. Min Act: -0.0000

Data Index: 838608 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.6462. Min Act: 0.0000

Data Index: 1186110 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7240. Min Act: -0.0000

Data Index: 506012 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.5858. Min Act: -0.0000

Data Index: 1200105 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.5723. Min Act: 0.0000

Data Index: 1010341 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.5003. Min Act: 0.0000

Data Index: 1153215 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.4444. Min Act: -0.0000

Data Index: 148694 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.3104. Min Act: 0.0000

Data Index: 1081179 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.4155. Min Act: -0.0000

Data Index: 46463 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.3292. Min Act: -0.0000

Data Index: 324727 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.3284. Min Act: 0.0000

Data Index: 398248 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.2596. Min Act: -0.0000

Data Index: 252426 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.2854. Min Act: -0.0000

Data Index: 570777 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.2579. Min Act: -0.0000

Data Index: 421496 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.3189. Min Act: 0.0000

Data Index: 425924 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.1760. Min Act: 0.0000

Data Index: 193286 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.1676. Min Act: -0.0000

Data Index: 436086 (C4 (Web Text))

Max Activating Token Index: 122