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

Dataset: Open Web Text

Neuron 405 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: 4.0807. Min Range: -4.0807

Max Act: 4.0807. Min Act: -0.1700

Data Index: 962446 (Open Web Text)

Max Activating Token Index: 978

Text #1

Max Range: 4.0807. Min Range: -4.0807

Max Act: 4.0804. Min Act: -0.1700

Data Index: 6773874 (Open Web Text)

Max Activating Token Index: 201

Text #2

Max Range: 4.0807. Min Range: -4.0807

Max Act: 4.0089. Min Act: -0.1700

Data Index: 7664784 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9969. Min Act: -0.1700

Data Index: 148656 (Open Web Text)

Max Activating Token Index: 996

Text #4

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9708. Min Act: -0.1700

Data Index: 4622998 (Open Web Text)

Max Activating Token Index: 649

Text #5

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9562. Min Act: -0.1700

Data Index: 6699775 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9378. Min Act: -0.1700

Data Index: 7370666 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9198. Min Act: -0.1700

Data Index: 3180322 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9938. Min Act: -0.1700

Data Index: 3708034 (Open Web Text)

Max Activating Token Index: 989

Text #9

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9030. Min Act: -0.1700

Data Index: 5764388 (Open Web Text)

Max Activating Token Index: 705

Text #10

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9234. Min Act: -0.1700

Data Index: 4839132 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9328. Min Act: -0.1700

Data Index: 6371851 (Open Web Text)

Max Activating Token Index: 87

Text #12

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8721. Min Act: -0.1700

Data Index: 3826407 (Open Web Text)

Max Activating Token Index: 992

Text #13

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8968. Min Act: -0.1700

Data Index: 2540994 (Open Web Text)

Max Activating Token Index: 1007

Text #14

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8918. Min Act: -0.1700

Data Index: 8504447 (Open Web Text)

Max Activating Token Index: 1015

Text #15

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8473. Min Act: -0.1700

Data Index: 8804144 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8689. Min Act: -0.1700

Data Index: 2232921 (Open Web Text)

Max Activating Token Index: 61

Text #17

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8579. Min Act: -0.1700

Data Index: 8280094 (Open Web Text)

Max Activating Token Index: 658

Text #18

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9151. Min Act: -0.1700

Data Index: 4935522 (Open Web Text)

Max Activating Token Index: 91

Text #19

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9049. Min Act: -0.1700

Data Index: 1998810 (Open Web Text)

Max Activating Token Index: 633