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

Dataset: Open Web Text

Neuron 759 in Layer 2

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: 1.8883. Min Range: -1.8883

Max Act: 1.8883. Min Act: -0.1700

Data Index: 7756122 (Open Web Text)

Max Activating Token Index: 358

Text #1

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.8627. Min Act: -0.1700

Data Index: 8235717 (Open Web Text)

Max Activating Token Index: 1003

Text #2

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.8017. Min Act: -0.1700

Data Index: 2374790 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.8182. Min Act: -0.1700

Data Index: 2720832 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.8153. Min Act: -0.1698

Data Index: 7063687 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7889. Min Act: -0.1700

Data Index: 5078744 (Open Web Text)

Max Activating Token Index: 486

Text #6

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7855. Min Act: -0.1700

Data Index: 4859795 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7950. Min Act: -0.1700

Data Index: 3123682 (Open Web Text)

Max Activating Token Index: 331

Text #8

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7771. Min Act: -0.1700

Data Index: 1871427 (Open Web Text)

Max Activating Token Index: 277

Text #9

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.8001. Min Act: -0.1700

Data Index: 3728189 (Open Web Text)

Max Activating Token Index: 834

Text #10

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.8101. Min Act: -0.1700

Data Index: 6239934 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7925. Min Act: -0.1700

Data Index: 2640163 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7662. Min Act: -0.1700

Data Index: 8583343 (Open Web Text)

Max Activating Token Index: 233

Text #13

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7767. Min Act: -0.1700

Data Index: 6735908 (Open Web Text)

Max Activating Token Index: 637

Text #14

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7905. Min Act: -0.1700

Data Index: 6299347 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7679. Min Act: -0.1700

Data Index: 7752421 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7585. Min Act: -0.1700

Data Index: 2174798 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7806. Min Act: -0.1700

Data Index: 7289688 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7736. Min Act: -0.1700

Data Index: 8314607 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7383. Min Act: -0.1700

Data Index: 3723276 (Open Web Text)

Max Activating Token Index: 1016