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

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

Neuron 1767 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1976. Min Act: -0.1700

Data Index: 829276 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.2133. Min Act: -0.1700

Data Index: 349115 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.2133. Min Act: -0.1700

Data Index: 32739 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1819. Min Act: -0.1700

Data Index: 531048 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1819. Min Act: -0.1700

Data Index: 325812 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1819. Min Act: -0.1700

Data Index: 94877 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1819. Min Act: -0.1700

Data Index: 1030233 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1819. Min Act: -0.1700

Data Index: 1348417 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1819. Min Act: -0.1700

Data Index: 1126930 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1819. Min Act: -0.1700

Data Index: 144542 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1661. Min Act: -0.1700

Data Index: 1465815 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1661. Min Act: -0.1700

Data Index: 1121537 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1661. Min Act: -0.1700

Data Index: 392280 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1661. Min Act: -0.1700

Data Index: 904938 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1661. Min Act: -0.1700

Data Index: 974849 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1504. Min Act: -0.1700

Data Index: 1279291 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1504. Min Act: -0.1700

Data Index: 408122 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1346. Min Act: -0.1700

Data Index: 984072 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1346. Min Act: -0.1700

Data Index: 897533 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 3.2133. Min Range: -3.2133

Max Act: 3.1346. Min Act: -0.1700

Data Index: 1088088 (C4 (Web Text))

Max Activating Token Index: 703