Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1578 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.8430. Min Act: -0.1700

Data Index: 1528047 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.7491. Min Act: -0.1700

Data Index: 1374867 (Python Code)

Max Activating Token Index: 533

Text #2

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.7491. Min Act: -0.1700

Data Index: 1572434 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.7178. Min Act: -0.1700

Data Index: 1623719 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.5926. Min Act: -0.1700

Data Index: 1364417 (Python Code)

Max Activating Token Index: 325

Text #5

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.5926. Min Act: -0.1700

Data Index: 1370028 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.5926. Min Act: -0.1700

Data Index: 1572853 (Python Code)

Max Activating Token Index: 694

Text #7

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1606477 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1608958 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1543980 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.5300. Min Act: -0.1700

Data Index: 1460245 (Python Code)

Max Activating Token Index: 391

Text #11

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.5300. Min Act: -0.1700

Data Index: 1563025 (Python Code)

Max Activating Token Index: 167

Text #12

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.4986. Min Act: -0.1700

Data Index: 1466944 (Python Code)

Max Activating Token Index: 372

Text #13

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.4986. Min Act: -0.1700

Data Index: 815046 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.4673. Min Act: -0.1700

Data Index: 718697 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.4986. Min Act: -0.1700

Data Index: 1630298 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.4673. Min Act: -0.1700

Data Index: 1635342 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.4673. Min Act: -0.1700

Data Index: 1149314 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.4046. Min Act: -0.1700

Data Index: 1595945 (Python Code)

Max Activating Token Index: 431

Text #19

Max Range: 3.8430. Min Range: -3.8430

Max Act: 3.4360. Min Act: -0.1700

Data Index: 1387516 (Python Code)

Max Activating Token Index: 137