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

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

Neuron 3059 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: 0.8994. Min Range: -0.8994

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1548761 (Python Code)

Max Activating Token Index: 438

Text #1

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1568737 (Python Code)

Max Activating Token Index: 512

Text #2

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1395890 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1512666 (Python Code)

Max Activating Token Index: 906

Text #4

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1421964 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1537609 (Python Code)

Max Activating Token Index: 273

Text #6

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1578274 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1495760 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1470808 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1430819 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1653837 (Python Code)

Max Activating Token Index: 525

Text #11

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1578759 (Python Code)

Max Activating Token Index: 243

Text #12

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1594736 (Python Code)

Max Activating Token Index: 767

Text #13

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1380049 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1529943 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1528879 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1606154 (Python Code)

Max Activating Token Index: 846

Text #17

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1592912 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1432098 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1370191 (Python Code)

Max Activating Token Index: 397