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

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

Neuron 674 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: 5.0634. Min Range: -5.0634

Max Act: 5.0634. Min Act: -0.1700

Data Index: 1282456 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.9072. Min Act: -0.1700

Data Index: 1262863 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.8447. Min Act: -0.1700

Data Index: 835708 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.7509. Min Act: -0.1700

Data Index: 437045 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.8134. Min Act: -0.1700

Data Index: 1096754 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.7509. Min Act: -0.1700

Data Index: 226040 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.7822. Min Act: -0.1700

Data Index: 1152692 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.7509. Min Act: -0.1700

Data Index: 1266488 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6259. Min Act: -0.1700

Data Index: 491260 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6884. Min Act: -0.1700

Data Index: 571392 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6259. Min Act: -0.1700

Data Index: 339419 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.7509. Min Act: -0.1700

Data Index: 1288169 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6884. Min Act: -0.1700

Data Index: 1111035 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6884. Min Act: -0.1700

Data Index: 91054 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6259. Min Act: -0.1700

Data Index: 681731 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6572. Min Act: -0.1700

Data Index: 762151 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.5634. Min Act: -0.1700

Data Index: 778232 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6572. Min Act: -0.1700

Data Index: 833890 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.5634. Min Act: -0.1700

Data Index: 936803 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 5.0634. Min Range: -5.0634

Max Act: 4.6884. Min Act: -0.1700

Data Index: 1176420 (C4 (Web Text))

Max Activating Token Index: 367