Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1378 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.8753. Min Act: -0.1700

Data Index: 1602528 (Python Code)

Max Activating Token Index: 883

Text #1

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.5003. Min Act: -0.1700

Data Index: 1362759 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.3753. Min Act: -0.1700

Data Index: 1505116 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.4378. Min Act: -0.1700

Data Index: 1457315 (Python Code)

Max Activating Token Index: 649

Text #4

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.3128. Min Act: -0.1700

Data Index: 1496038 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.2816. Min Act: -0.1700

Data Index: 1434475 (Python Code)

Max Activating Token Index: 996

Text #6

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.2191. Min Act: -0.1700

Data Index: 814249 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.1566. Min Act: -0.1700

Data Index: 1482962 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.2503. Min Act: -0.1700

Data Index: 1500956 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.1878. Min Act: -0.1700

Data Index: 918874 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.0941. Min Act: -0.1700

Data Index: 1523965 (Python Code)

Max Activating Token Index: 855

Text #11

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.0003. Min Act: -0.1700

Data Index: 1508163 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.1878. Min Act: -0.1700

Data Index: 1533826 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.1253. Min Act: -0.1700

Data Index: 1439803 (Python Code)

Max Activating Token Index: 557

Text #14

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.1566. Min Act: -0.1700

Data Index: 1498315 (Python Code)

Max Activating Token Index: 786

Text #15

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.0941. Min Act: -0.1700

Data Index: 1463809 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.0316. Min Act: -0.1700

Data Index: 1435691 (Python Code)

Max Activating Token Index: 941

Text #17

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.0628. Min Act: -0.1700

Data Index: 1409918 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.1253. Min Act: -0.1700

Data Index: 1531164 (Python Code)

Max Activating Token Index: 597

Text #19

Max Range: 7.8753. Min Range: -7.8753

Max Act: 7.1566. Min Act: -0.1700

Data Index: 1474225 (Python Code)

Max Activating Token Index: 986