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

Dataset: Open Web Text

Neuron 27 in Layer 5

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: 4.9250. Min Range: -4.9250

Max Act: 4.9250. Min Act: -0.1700

Data Index: 1139287 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.8572. Min Act: -0.1700

Data Index: 8743826 (Open Web Text)

Max Activating Token Index: 480

Text #2

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7705. Min Act: -0.1700

Data Index: 2100927 (Open Web Text)

Max Activating Token Index: 467

Text #3

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7766. Min Act: -0.1700

Data Index: 298807 (Open Web Text)

Max Activating Token Index: 130

Text #4

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7494. Min Act: -0.1700

Data Index: 5638561 (Open Web Text)

Max Activating Token Index: 285

Text #5

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.6869. Min Act: -0.1700

Data Index: 155664 (Open Web Text)

Max Activating Token Index: 653

Text #6

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.6635. Min Act: -0.1700

Data Index: 4023763 (Open Web Text)

Max Activating Token Index: 568

Text #7

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7799. Min Act: -0.1700

Data Index: 6173975 (Open Web Text)

Max Activating Token Index: 580

Text #8

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7417. Min Act: -0.1700

Data Index: 2870693 (Open Web Text)

Max Activating Token Index: 233

Text #9

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7140. Min Act: -0.1700

Data Index: 4119316 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7048. Min Act: -0.1700

Data Index: 4432202 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7075. Min Act: -0.1700

Data Index: 5622666 (Open Web Text)

Max Activating Token Index: 127

Text #12

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7112. Min Act: -0.1700

Data Index: 8627445 (Open Web Text)

Max Activating Token Index: 520

Text #13

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7030. Min Act: -0.1700

Data Index: 277193 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.6756. Min Act: -0.1700

Data Index: 3318947 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.6864. Min Act: -0.1700

Data Index: 708292 (Open Web Text)

Max Activating Token Index: 717

Text #16

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.6990. Min Act: -0.1700

Data Index: 5784483 (Open Web Text)

Max Activating Token Index: 141

Text #17

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.7148. Min Act: -0.1700

Data Index: 5654603 (Open Web Text)

Max Activating Token Index: 330

Text #18

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.6780. Min Act: -0.1700

Data Index: 632795 (Open Web Text)

Max Activating Token Index: 499

Text #19

Max Range: 4.9250. Min Range: -4.9250

Max Act: 4.6631. Min Act: -0.1700

Data Index: 3454874 (Open Web Text)

Max Activating Token Index: 703