Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1007 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.8501. Min Act: -0.1700

Data Index: 2350270 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.8138. Min Act: -0.1700

Data Index: 1071013 (Open Web Text)

Max Activating Token Index: 763

Text #2

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7880. Min Act: -0.1700

Data Index: 7603442 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7699. Min Act: -0.1700

Data Index: 6402601 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7929. Min Act: -0.1700

Data Index: 3412251 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7212. Min Act: -0.1700

Data Index: 8085826 (Open Web Text)

Max Activating Token Index: 201

Text #6

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7395. Min Act: -0.1700

Data Index: 3066001 (Open Web Text)

Max Activating Token Index: 528

Text #7

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1600376 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7096. Min Act: -0.1700

Data Index: 976514 (Open Web Text)

Max Activating Token Index: 391

Text #9

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6978. Min Act: -0.1700

Data Index: 701946 (Open Web Text)

Max Activating Token Index: 104

Text #10

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7119. Min Act: -0.1700

Data Index: 3681141 (Open Web Text)

Max Activating Token Index: 130

Text #11

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7070. Min Act: -0.1700

Data Index: 5444756 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6942. Min Act: -0.1700

Data Index: 5013182 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6396. Min Act: -0.1700

Data Index: 6162035 (Open Web Text)

Max Activating Token Index: 573

Text #14

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6549. Min Act: -0.1700

Data Index: 6357645 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6406. Min Act: -0.1700

Data Index: 5759464 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6838. Min Act: -0.1700

Data Index: 5341035 (Open Web Text)

Max Activating Token Index: 1004

Text #17

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6579. Min Act: -0.1700

Data Index: 3485708 (Open Web Text)

Max Activating Token Index: 127

Text #18

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6891. Min Act: -0.1700

Data Index: 1087140 (Open Web Text)

Max Activating Token Index: 619

Text #19

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6701. Min Act: -0.1700

Data Index: 7594191 (Open Web Text)

Max Activating Token Index: 184