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

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

Neuron 888 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4682. Min Act: -0.1700

Data Index: 633562 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4525. Min Act: -0.1700

Data Index: 726207 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4525. Min Act: -0.1700

Data Index: 1046295 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4368. Min Act: -0.1700

Data Index: 1103560 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4368. Min Act: -0.1700

Data Index: 1252942 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4368. Min Act: -0.1700

Data Index: 805870 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4368. Min Act: -0.1700

Data Index: 719984 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4211. Min Act: -0.1700

Data Index: 87449 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3898. Min Act: -0.1700

Data Index: 637073 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4054. Min Act: -0.1700

Data Index: 1274149 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4054. Min Act: -0.1700

Data Index: 1056406 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3741. Min Act: -0.1700

Data Index: 1190853 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.4054. Min Act: -0.1700

Data Index: 580323 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3898. Min Act: -0.1700

Data Index: 1349669 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3741. Min Act: -0.1700

Data Index: 73092 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3898. Min Act: -0.1700

Data Index: 893776 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3898. Min Act: -0.1700

Data Index: 936338 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3741. Min Act: -0.1700

Data Index: 483335 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3741. Min Act: -0.1700

Data Index: 1070066 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 3.4682. Min Range: -3.4682

Max Act: 3.3741. Min Act: -0.1700

Data Index: 536665 (C4 (Web Text))

Max Activating Token Index: 339