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

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

Neuron 5914 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.8023. Min Act: -0.0000

Data Index: 1413254 (Python Code)

Max Activating Token Index: 883

Text #1

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.8701. Min Act: -0.0000

Data Index: 1412054 (Python Code)

Max Activating Token Index: 717

Text #2

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.7719. Min Act: -0.0000

Data Index: 1470762 (Python Code)

Max Activating Token Index: 876

Text #3

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.3444. Min Act: -0.0000

Data Index: 1422553 (Python Code)

Max Activating Token Index: 875

Text #4

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.6773. Min Act: -0.0000

Data Index: 1448882 (Python Code)

Max Activating Token Index: 1012

Text #5

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.2646. Min Act: -0.0000

Data Index: 1619709 (Python Code)

Max Activating Token Index: 829

Text #6

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.6424. Min Act: -0.0000

Data Index: 1389880 (Python Code)

Max Activating Token Index: 90

Text #7

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.8937. Min Act: -0.0000

Data Index: 1585614 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.6773. Min Act: -0.0000

Data Index: 1571445 (Python Code)

Max Activating Token Index: 539

Text #9

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.5412. Min Act: -0.0000

Data Index: 1389182 (Python Code)

Max Activating Token Index: 465

Text #10

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.5134. Min Act: -0.0000

Data Index: 1435101 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.4806. Min Act: -0.0000

Data Index: 1546458 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.3493. Min Act: -0.0000

Data Index: 1439072 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.3910. Min Act: -0.0000

Data Index: 1598108 (Python Code)

Max Activating Token Index: 847

Text #14

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.5726. Min Act: -0.0000

Data Index: 1388569 (Python Code)

Max Activating Token Index: 712

Text #15

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.3549. Min Act: -0.0000

Data Index: 1434604 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.2239. Min Act: -0.0000

Data Index: 1452273 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.2057. Min Act: -0.0000

Data Index: 1510311 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.5320. Min Act: -0.0000

Data Index: 1367227 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 2.8937. Min Range: -2.8937

Max Act: 2.5367. Min Act: -0.0000

Data Index: 1545832 (Python Code)

Max Activating Token Index: 555