Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1821 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0441. Min Range: -5.0441

Max Act: 5.0441. Min Act: -0.1699

Data Index: 1415127 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 5.0441. Min Range: -5.0441

Max Act: 5.0441. Min Act: -0.1700

Data Index: 1574717 (Python Code)

Max Activating Token Index: 665

Text #2

Max Range: 5.0441. Min Range: -5.0441

Max Act: 5.0441. Min Act: -0.1700

Data Index: 1417102 (Python Code)

Max Activating Token Index: 553

Text #3

Max Range: 5.0441. Min Range: -5.0441

Max Act: 5.0129. Min Act: -0.1700

Data Index: 1529662 (Python Code)

Max Activating Token Index: 826

Text #4

Max Range: 5.0441. Min Range: -5.0441

Max Act: 5.0129. Min Act: -0.1700

Data Index: 1585850 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 5.0441. Min Range: -5.0441

Max Act: 5.0129. Min Act: -0.1700

Data Index: 1386801 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.9504. Min Act: -0.1700

Data Index: 1512783 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.9816. Min Act: -0.1700

Data Index: 1637370 (Python Code)

Max Activating Token Index: 706

Text #8

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8879. Min Act: -0.1700

Data Index: 1563120 (Python Code)

Max Activating Token Index: 553

Text #9

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.9191. Min Act: -0.1700

Data Index: 1560647 (Python Code)

Max Activating Token Index: 173

Text #10

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.9191. Min Act: -0.1700

Data Index: 1397484 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8879. Min Act: -0.1700

Data Index: 1568223 (Python Code)

Max Activating Token Index: 771

Text #12

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8566. Min Act: -0.1700

Data Index: 1554729 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8566. Min Act: -0.1700

Data Index: 1622527 (Python Code)

Max Activating Token Index: 915

Text #14

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8879. Min Act: -0.1700

Data Index: 1551338 (Python Code)

Max Activating Token Index: 864

Text #15

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8879. Min Act: -0.1700

Data Index: 1417363 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8879. Min Act: -0.1700

Data Index: 1481969 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8879. Min Act: -0.1700

Data Index: 1481716 (Python Code)

Max Activating Token Index: 937

Text #18

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8566. Min Act: -0.1700

Data Index: 1528310 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 5.0441. Min Range: -5.0441

Max Act: 4.8566. Min Act: -0.1700

Data Index: 1480623 (Python Code)

Max Activating Token Index: 556