Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3559 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.9616. Min Act: -0.0001

Data Index: 1364331 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.8159. Min Act: -0.0001

Data Index: 1558707 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1481742 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1360616 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7388. Min Act: -0.0001

Data Index: 1407929 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1466073 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7430. Min Act: -0.0001

Data Index: 1425086 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1623431 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1466899 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1366719 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1618295 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6735. Min Act: -0.0001

Data Index: 1565849 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1418523 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1392940 (Python Code)

Max Activating Token Index: 1012

Text #14

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1439974 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6814. Min Act: -0.0001

Data Index: 1521390 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6788. Min Act: -0.0001

Data Index: 1627550 (Python Code)

Max Activating Token Index: 510

Text #17

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1436372 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1621508 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1622747 (Python Code)

Max Activating Token Index: 10