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

Dataset: Open Web Text

Neuron 714 in Layer 1

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: 1.8523. Min Range: -1.8523

Max Act: 1.8523. Min Act: -0.1700

Data Index: 6697580 (Open Web Text)

Max Activating Token Index: 877

Text #1

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7933. Min Act: -0.1700

Data Index: 2162871 (Open Web Text)

Max Activating Token Index: 723

Text #2

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7555. Min Act: -0.1700

Data Index: 8454608 (Open Web Text)

Max Activating Token Index: 123

Text #3

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7588. Min Act: -0.1700

Data Index: 6875798 (Open Web Text)

Max Activating Token Index: 323

Text #4

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7592. Min Act: -0.1700

Data Index: 1442913 (Open Web Text)

Max Activating Token Index: 759

Text #5

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7435. Min Act: -0.1700

Data Index: 3683266 (Open Web Text)

Max Activating Token Index: 469

Text #6

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7041. Min Act: -0.1700

Data Index: 6400836 (Open Web Text)

Max Activating Token Index: 255

Text #7

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7037. Min Act: -0.1700

Data Index: 2244520 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7005. Min Act: -0.1700

Data Index: 565377 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7004. Min Act: -0.1700

Data Index: 4611558 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7016. Min Act: -0.1700

Data Index: 2885775 (Open Web Text)

Max Activating Token Index: 109

Text #11

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7017. Min Act: -0.1700

Data Index: 7249974 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6995. Min Act: -0.1700

Data Index: 242420 (Open Web Text)

Max Activating Token Index: 142

Text #13

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.7029. Min Act: -0.1700

Data Index: 5099476 (Open Web Text)

Max Activating Token Index: 993

Text #14

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6908. Min Act: -0.1700

Data Index: 4256736 (Open Web Text)

Max Activating Token Index: 65

Text #15

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6926. Min Act: -0.1700

Data Index: 1809951 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6898. Min Act: -0.1700

Data Index: 6066274 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6942. Min Act: -0.1700

Data Index: 7301205 (Open Web Text)

Max Activating Token Index: 134

Text #18

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6982. Min Act: -0.1700

Data Index: 5017360 (Open Web Text)

Max Activating Token Index: 483

Text #19

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6917. Min Act: -0.1700

Data Index: 13379 (Open Web Text)

Max Activating Token Index: 805