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

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

Neuron 3640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1263415 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.4845. Min Act: -0.0000

Data Index: 1280275 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.3273. Min Act: -0.0000

Data Index: 510640 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.2350. Min Act: -0.0000

Data Index: 536011 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1225081 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1194. Min Act: -0.0000

Data Index: 497403 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1320. Min Act: -0.0000

Data Index: 525936 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1151. Min Act: -0.0000

Data Index: 1049253 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1106158 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9833. Min Act: -0.0000

Data Index: 961292 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1083139 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1315930 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9454. Min Act: -0.0000

Data Index: 262006 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9679. Min Act: -0.0000

Data Index: 368900 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9139. Min Act: -0.0000

Data Index: 216049 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9180. Min Act: -0.0000

Data Index: 159973 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.8827. Min Act: -0.0000

Data Index: 280512 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9377. Min Act: -0.0000

Data Index: 166663 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.9400. Min Act: -0.0000

Data Index: 844162 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.5397. Min Range: -1.5397

Max Act: 0.8798. Min Act: -0.0000

Data Index: 107360 (C4 (Web Text))

Max Activating Token Index: 137