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

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

Neuron 1962 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: 5.9547. Min Range: -5.9547

Max Act: 5.9547. Min Act: -0.1700

Data Index: 1311226 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.7359. Min Act: -0.1700

Data Index: 750746 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.7359. Min Act: -0.1700

Data Index: 1186913 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.6109. Min Act: -0.1700

Data Index: 658192 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.6422. Min Act: -0.1700

Data Index: 1331170 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.6734. Min Act: -0.1700

Data Index: 1351041 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.5797. Min Act: -0.1699

Data Index: 347617 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.5797. Min Act: -0.1700

Data Index: 1015382 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.5484. Min Act: -0.1700

Data Index: 792831 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.5484. Min Act: -0.1700

Data Index: 108849 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.4859. Min Act: -0.1700

Data Index: 551460 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.4547. Min Act: -0.1700

Data Index: 1355140 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.4547. Min Act: -0.1700

Data Index: 285612 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.4547. Min Act: -0.1698

Data Index: 1143798 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.4859. Min Act: -0.1700

Data Index: 244841 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.4547. Min Act: -0.1700

Data Index: 1294038 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.4547. Min Act: -0.1700

Data Index: 548526 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.3922. Min Act: -0.1700

Data Index: 1061385 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.3609. Min Act: -0.1700

Data Index: 539608 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 5.9547. Min Range: -5.9547

Max Act: 5.3297. Min Act: -0.1700

Data Index: 484696 (C4 (Web Text))

Max Activating Token Index: 843