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

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

Neuron 911 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.4094. Min Act: -0.0000

Data Index: 749410 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1575234 (Python Code)

Max Activating Token Index: 947

Text #2

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.4450. Min Act: -0.0000

Data Index: 31770 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1633906 (Python Code)

Max Activating Token Index: 373

Text #4

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1976. Min Act: -0.0000

Data Index: 1606479 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1926. Min Act: -0.0001

Data Index: 1552354 (Python Code)

Max Activating Token Index: 375

Text #6

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1643466 (Python Code)

Max Activating Token Index: 534

Text #7

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1529222 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1565668 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1501426 (Python Code)

Max Activating Token Index: 937

Text #10

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1467786 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1562057 (Python Code)

Max Activating Token Index: 997

Text #12

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1466. Min Act: -0.0001

Data Index: 1616123 (Python Code)

Max Activating Token Index: 368

Text #13

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1635892 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 1.4450. Min Range: -1.4450

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1500268 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1404259 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1606096 (Python Code)

Max Activating Token Index: 384

Text #17

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0579. Min Act: -0.0000

Data Index: 1592953 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1510953 (Python Code)

Max Activating Token Index: 337

Text #19

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1466. Min Act: -0.0000

Data Index: 1415450 (Python Code)

Max Activating Token Index: 266