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

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

Neuron 2582 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.5206. Min Act: -0.0001

Data Index: 1651627 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.5229. Min Act: -0.0001

Data Index: 1580083 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.3612. Min Act: -0.0001

Data Index: 1536993 (Python Code)

Max Activating Token Index: 517

Text #3

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.2175. Min Act: -0.0001

Data Index: 1629706 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0530. Min Act: -0.0001

Data Index: 1563802 (Python Code)

Max Activating Token Index: 577

Text #5

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0450. Min Act: -0.0001

Data Index: 1413514 (Python Code)

Max Activating Token Index: 782

Text #6

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0595. Min Act: -0.0001

Data Index: 1382992 (Python Code)

Max Activating Token Index: 615

Text #7

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.1232. Min Act: -0.0001

Data Index: 1369093 (Python Code)

Max Activating Token Index: 936

Text #8

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0445. Min Act: -0.0001

Data Index: 1405681 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.1349. Min Act: -0.0001

Data Index: 1458930 (Python Code)

Max Activating Token Index: 397

Text #10

Max Range: 1.5229. Min Range: -1.5229

Max Act: 0.9968. Min Act: -0.0001

Data Index: 1378658 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.1106. Min Act: -0.0001

Data Index: 1450827 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0863. Min Act: -0.0001

Data Index: 1381576 (Python Code)

Max Activating Token Index: 553

Text #13

Max Range: 1.5229. Min Range: -1.5229

Max Act: 0.9470. Min Act: -0.0001

Data Index: 1581484 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0397. Min Act: -0.0001

Data Index: 1603037 (Python Code)

Max Activating Token Index: 135

Text #15

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0554. Min Act: -0.0001

Data Index: 1364481 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0825. Min Act: -0.0001

Data Index: 1453807 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0423. Min Act: -0.0001

Data Index: 1480397 (Python Code)

Max Activating Token Index: 112

Text #18

Max Range: 1.5229. Min Range: -1.5229

Max Act: 0.9879. Min Act: -0.0001

Data Index: 1550587 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0128. Min Act: -0.0001

Data Index: 1592053 (Python Code)

Max Activating Token Index: 43