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

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

Neuron 2603 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: 1.2223. Min Range: -1.2223

Max Act: 1.2223. Min Act: -0.0000

Data Index: 1476727 (Python Code)

Max Activating Token Index: 563

Text #1

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1452678 (Python Code)

Max Activating Token Index: 418

Text #2

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1397219 (Python Code)

Max Activating Token Index: 934

Text #3

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1599056 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1615290 (Python Code)

Max Activating Token Index: 413

Text #5

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1528160 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.7799. Min Act: -0.0001

Data Index: 1455015 (Python Code)

Max Activating Token Index: 998

Text #7

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1480493 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1472109 (Python Code)

Max Activating Token Index: 752

Text #9

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1377357 (Python Code)

Max Activating Token Index: 368

Text #10

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1418768 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1468271 (Python Code)

Max Activating Token Index: 779

Text #12

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1568259 (Python Code)

Max Activating Token Index: 860

Text #13

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1553457 (Python Code)

Max Activating Token Index: 276

Text #14

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1614680 (Python Code)

Max Activating Token Index: 969

Text #15

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1554970 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1554090 (Python Code)

Max Activating Token Index: 841

Text #17

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1458414 (Python Code)

Max Activating Token Index: 672

Text #18

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1385925 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1442817 (Python Code)

Max Activating Token Index: 750