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

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

Neuron 1221 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.7849. Min Act: -0.1700

Data Index: 1445753 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.7224. Min Act: -0.1700

Data Index: 1457270 (Python Code)

Max Activating Token Index: 936

Text #2

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.7224. Min Act: -0.1700

Data Index: 1499592 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.7224. Min Act: -0.1700

Data Index: 1530731 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.5974. Min Act: -0.1700

Data Index: 1570167 (Python Code)

Max Activating Token Index: 537

Text #5

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.5349. Min Act: -0.1700

Data Index: 1584474 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.5974. Min Act: -0.1700

Data Index: 1460590 (Python Code)

Max Activating Token Index: 541

Text #7

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4099. Min Act: -0.1700

Data Index: 1477194 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.5349. Min Act: -0.1700

Data Index: 1541255 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4724. Min Act: -0.1700

Data Index: 1467791 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.5349. Min Act: -0.1700

Data Index: 1470826 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4724. Min Act: -0.1700

Data Index: 1422350 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4099. Min Act: -0.1698

Data Index: 1524090 (Python Code)

Max Activating Token Index: 761

Text #13

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4724. Min Act: -0.1700

Data Index: 1549514 (Python Code)

Max Activating Token Index: 553

Text #14

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4099. Min Act: -0.1700

Data Index: 1648959 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4099. Min Act: -0.1700

Data Index: 1376758 (Python Code)

Max Activating Token Index: 364

Text #16

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4099. Min Act: -0.1700

Data Index: 1563762 (Python Code)

Max Activating Token Index: 955

Text #17

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.4099. Min Act: -0.1700

Data Index: 1507620 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.3162. Min Act: -0.1700

Data Index: 1641603 (Python Code)

Max Activating Token Index: 403

Text #19

Max Range: 7.7849. Min Range: -7.7849

Max Act: 7.3162. Min Act: -0.1700

Data Index: 1529235 (Python Code)

Max Activating Token Index: 906