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

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

Neuron 3813 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: 5.8073. Min Range: -5.8073

Max Act: 5.8073. Min Act: -0.0000

Data Index: 1503448 (Python Code)

Max Activating Token Index: 758

Text #1

Max Range: 5.8073. Min Range: -5.8073

Max Act: 5.5914. Min Act: -0.0000

Data Index: 1564998 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 5.8073. Min Range: -5.8073

Max Act: 5.5310. Min Act: -0.0000

Data Index: 1598065 (Python Code)

Max Activating Token Index: 262

Text #3

Max Range: 5.8073. Min Range: -5.8073

Max Act: 5.1706. Min Act: -0.0000

Data Index: 1644198 (Python Code)

Max Activating Token Index: 972

Text #4

Max Range: 5.8073. Min Range: -5.8073

Max Act: 5.0255. Min Act: -0.0000

Data Index: 1536722 (Python Code)

Max Activating Token Index: 581

Text #5

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.8160. Min Act: -0.0000

Data Index: 1439813 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.9492. Min Act: -0.0000

Data Index: 1381335 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.8233. Min Act: -0.0000

Data Index: 1414825 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.9684. Min Act: -0.0000

Data Index: 1460895 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.6032. Min Act: -0.0000

Data Index: 1548312 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.9417. Min Act: -0.0000

Data Index: 1368706 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.7239. Min Act: -0.0000

Data Index: 1420892 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.6671. Min Act: -0.0000

Data Index: 1568822 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.5621. Min Act: -0.0000

Data Index: 1499167 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.6774. Min Act: -0.0000

Data Index: 1587598 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.2637. Min Act: -0.0000

Data Index: 1384588 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.4459. Min Act: -0.0000

Data Index: 1588020 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.5573. Min Act: -0.0000

Data Index: 1424784 (Python Code)

Max Activating Token Index: 336

Text #18

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.5619. Min Act: -0.0000

Data Index: 1487519 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 5.8073. Min Range: -5.8073

Max Act: 4.5543. Min Act: -0.0000

Data Index: 1520747 (Python Code)

Max Activating Token Index: 870