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

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

Neuron 702 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.5583. Min Act: -0.1700

Data Index: 1591288 (Python Code)

Max Activating Token Index: 355

Text #1

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.5422. Min Act: -0.1700

Data Index: 1505781 (Python Code)

Max Activating Token Index: 693

Text #2

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.5099. Min Act: -0.1700

Data Index: 1503708 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4937. Min Act: -0.1700

Data Index: 1448525 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4937. Min Act: -0.1700

Data Index: 1365890 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4774. Min Act: -0.1700

Data Index: 1438290 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4450. Min Act: -0.1700

Data Index: 1342227 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4774. Min Act: -0.1700

Data Index: 1486043 (Python Code)

Max Activating Token Index: 513

Text #8

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4612. Min Act: -0.1700

Data Index: 1609450 (Python Code)

Max Activating Token Index: 703

Text #9

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4612. Min Act: -0.1700

Data Index: 1473114 (Python Code)

Max Activating Token Index: 602

Text #10

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4612. Min Act: -0.1700

Data Index: 1612466 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4612. Min Act: -0.1700

Data Index: 1416144 (Python Code)

Max Activating Token Index: 126

Text #12

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4612. Min Act: -0.1700

Data Index: 1573833 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4612. Min Act: -0.1700

Data Index: 1585215 (Python Code)

Max Activating Token Index: 434

Text #14

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4612. Min Act: -0.1700

Data Index: 136589 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4450. Min Act: -0.1700

Data Index: 1381305 (Python Code)

Max Activating Token Index: 145

Text #16

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4450. Min Act: -0.1700

Data Index: 1446259 (Python Code)

Max Activating Token Index: 334

Text #17

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4287. Min Act: -0.1700

Data Index: 1472297 (Python Code)

Max Activating Token Index: 989

Text #18

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4287. Min Act: -0.1700

Data Index: 1404898 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4287. Min Act: -0.1700

Data Index: 1498942 (Python Code)

Max Activating Token Index: 454