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

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

Neuron 5502 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2937. Min Range: -5.2937

Max Act: 5.2937. Min Act: -0.0000

Data Index: 1401591 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.9801. Min Act: -0.0000

Data Index: 1471949 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.9339. Min Act: -0.0000

Data Index: 1647233 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.4816. Min Act: -0.0000

Data Index: 1431974 (Python Code)

Max Activating Token Index: 424

Text #4

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.3059. Min Act: -0.0000

Data Index: 1469879 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.4543. Min Act: -0.0000

Data Index: 1463891 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.3949. Min Act: -0.0000

Data Index: 1494670 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.7529. Min Act: -0.0000

Data Index: 1448879 (Python Code)

Max Activating Token Index: 657

Text #8

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.9353. Min Act: -0.0000

Data Index: 1614117 (Python Code)

Max Activating Token Index: 268

Text #9

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.3806. Min Act: -0.0000

Data Index: 1583486 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.7341. Min Act: -0.0000

Data Index: 1616795 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.6499. Min Act: -0.0000

Data Index: 1438041 (Python Code)

Max Activating Token Index: 191

Text #12

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.2635. Min Act: -0.0000

Data Index: 1628808 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.4301. Min Act: -0.0000

Data Index: 1478104 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.4399. Min Act: -0.0000

Data Index: 1536936 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.3810. Min Act: -0.0000

Data Index: 1529464 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.2011. Min Act: -0.0000

Data Index: 1600522 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.2348. Min Act: -0.0000

Data Index: 1550261 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.5319. Min Act: -0.0000

Data Index: 1411961 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.3840. Min Act: -0.0000

Data Index: 1376413 (Python Code)

Max Activating Token Index: 689