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

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

Neuron 2903 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.4820. Min Act: -0.0000

Data Index: 1482586 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.5637. Min Act: -0.0000

Data Index: 1591666 (Python Code)

Max Activating Token Index: 643

Text #2

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.5579. Min Act: -0.0000

Data Index: 1500524 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.6799. Min Act: -0.0000

Data Index: 1537015 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.7791. Min Act: -0.0000

Data Index: 1580550 (Python Code)

Max Activating Token Index: 820

Text #5

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.4979. Min Act: -0.0000

Data Index: 1482261 (Python Code)

Max Activating Token Index: 119

Text #6

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.7575. Min Act: -0.0000

Data Index: 1488594 (Python Code)

Max Activating Token Index: 775

Text #7

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.6189. Min Act: -0.0000

Data Index: 1547912 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.4357. Min Act: -0.0000

Data Index: 1366336 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.4599. Min Act: -0.0000

Data Index: 1567852 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.4238. Min Act: -0.0000

Data Index: 1438596 (Python Code)

Max Activating Token Index: 841

Text #11

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.6132. Min Act: -0.0000

Data Index: 1631566 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.3606. Min Act: -0.0000

Data Index: 1656700 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.3238. Min Act: -0.0000

Data Index: 1461086 (Python Code)

Max Activating Token Index: 183

Text #14

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.2036. Min Act: -0.0000

Data Index: 1387346 (Python Code)

Max Activating Token Index: 68

Text #15

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.2803. Min Act: -0.0000

Data Index: 1532031 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.1468. Min Act: -0.0000

Data Index: 1444009 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.0322. Min Act: -0.0000

Data Index: 1548462 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.3574. Min Act: -0.0000

Data Index: 1568880 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 2.7791. Min Range: -2.7791

Max Act: 2.1140. Min Act: -0.0000

Data Index: 1443214 (Python Code)

Max Activating Token Index: 533