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

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

Neuron 2895 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: 4.7430. Min Range: -4.7430

Max Act: 4.7430. Min Act: -0.0000

Data Index: 1542033 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 4.7430. Min Range: -4.7430

Max Act: 4.2454. Min Act: -0.0000

Data Index: 1513926 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 4.7430. Min Range: -4.7430

Max Act: 4.2523. Min Act: -0.0000

Data Index: 1495475 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 4.7430. Min Range: -4.7430

Max Act: 4.2234. Min Act: -0.0000

Data Index: 1405975 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 4.7430. Min Range: -4.7430

Max Act: 4.2580. Min Act: -0.0000

Data Index: 1593898 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.8666. Min Act: -0.0000

Data Index: 1425847 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 4.7430. Min Range: -4.7430

Max Act: 4.0247. Min Act: -0.0000

Data Index: 1519398 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 4.7430. Min Range: -4.7430

Max Act: 4.0157. Min Act: -0.0000

Data Index: 1526909 (Python Code)

Max Activating Token Index: 731

Text #8

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.9267. Min Act: -0.0000

Data Index: 1408326 (Python Code)

Max Activating Token Index: 596

Text #9

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.7277. Min Act: -0.0000

Data Index: 1460469 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.8752. Min Act: -0.0000

Data Index: 1494781 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.7036. Min Act: -0.0000

Data Index: 1537517 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.9724. Min Act: -0.0000

Data Index: 1429916 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.7945. Min Act: -0.0000

Data Index: 1379492 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.8826. Min Act: -0.0000

Data Index: 1519956 (Python Code)

Max Activating Token Index: 366

Text #15

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.7201. Min Act: -0.0000

Data Index: 1567411 (Python Code)

Max Activating Token Index: 558

Text #16

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.7260. Min Act: -0.0000

Data Index: 1444145 (Python Code)

Max Activating Token Index: 570

Text #17

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.6949. Min Act: -0.0000

Data Index: 1497074 (Python Code)

Max Activating Token Index: 728

Text #18

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.7156. Min Act: -0.0000

Data Index: 1536494 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 4.7430. Min Range: -4.7430

Max Act: 3.6787. Min Act: -0.0000

Data Index: 1439692 (Python Code)

Max Activating Token Index: 134