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

Dataset: Open Web Text

Neuron 3036 in Layer 0

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: 4.0420. Min Range: -4.0420

Max Act: 4.0420. Min Act: -0.1700

Data Index: 3741665 (Open Web Text)

Max Activating Token Index: 56

Text #1

Max Range: 4.0420. Min Range: -4.0420

Max Act: 4.0135. Min Act: -0.1700

Data Index: 299715 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 4.0420. Min Range: -4.0420

Max Act: 4.0203. Min Act: -0.1700

Data Index: 511810 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 4.0420. Min Range: -4.0420

Max Act: 4.0221. Min Act: -0.1700

Data Index: 7065545 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9724. Min Act: -0.1700

Data Index: 5083014 (Open Web Text)

Max Activating Token Index: 837

Text #5

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9943. Min Act: -0.1700

Data Index: 6709702 (Open Web Text)

Max Activating Token Index: 1002

Text #6

Max Range: 4.0420. Min Range: -4.0420

Max Act: 4.0019. Min Act: -0.1700

Data Index: 1574863 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9868. Min Act: -0.1700

Data Index: 5769787 (Open Web Text)

Max Activating Token Index: 739

Text #8

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9777. Min Act: -0.1700

Data Index: 7816101 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9795. Min Act: -0.1700

Data Index: 4534989 (Open Web Text)

Max Activating Token Index: 889

Text #10

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9930. Min Act: -0.1700

Data Index: 8008571 (Open Web Text)

Max Activating Token Index: 863

Text #11

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9586. Min Act: -0.1700

Data Index: 5066997 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9510. Min Act: -0.1700

Data Index: 4917618 (Open Web Text)

Max Activating Token Index: 687

Text #13

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9498. Min Act: -0.1700

Data Index: 2597628 (Open Web Text)

Max Activating Token Index: 525

Text #14

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9451. Min Act: -0.1700

Data Index: 6187774 (Open Web Text)

Max Activating Token Index: 712

Text #15

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9530. Min Act: -0.1700

Data Index: 6416576 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9515. Min Act: -0.1700

Data Index: 6672783 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9676. Min Act: -0.1700

Data Index: 4649328 (Open Web Text)

Max Activating Token Index: 931

Text #18

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9592. Min Act: -0.1700

Data Index: 4200817 (Open Web Text)

Max Activating Token Index: 551

Text #19

Max Range: 4.0420. Min Range: -4.0420

Max Act: 3.9569. Min Act: -0.1700

Data Index: 7134076 (Open Web Text)

Max Activating Token Index: 668