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

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

Neuron 1820 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.9747. Min Act: -0.1700

Data Index: 155367 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.9435. Min Act: -0.1700

Data Index: 383644 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.9122. Min Act: -0.1700

Data Index: 768315 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8496. Min Act: -0.1700

Data Index: 786632 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8809. Min Act: -0.1700

Data Index: 926307 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8496. Min Act: -0.1700

Data Index: 1164258 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8496. Min Act: -0.1700

Data Index: 128969 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8184. Min Act: -0.1700

Data Index: 73403 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8496. Min Act: -0.1700

Data Index: 507580 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8184. Min Act: -0.1700

Data Index: 844664 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8184. Min Act: -0.1700

Data Index: 171160 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8184. Min Act: -0.1700

Data Index: 26307 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8184. Min Act: -0.1700

Data Index: 755304 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.7871. Min Act: -0.1700

Data Index: 822643 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.8184. Min Act: -0.1700

Data Index: 1046340 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.7871. Min Act: -0.1700

Data Index: 559876 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1107172 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1107951 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.7871. Min Act: -0.1700

Data Index: 797744 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 3.9747. Min Range: -3.9747

Max Act: 3.7558. Min Act: -0.1700

Data Index: 135564 (C4 (Web Text))

Max Activating Token Index: 319