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

Dataset: Open Web Text

Neuron 1717 in Layer 4

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: 4.3239. Min Range: -4.3239

Max Act: 4.3239. Min Act: -0.1700

Data Index: 3235500 (Open Web Text)

Max Activating Token Index: 953

Text #1

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.2725. Min Act: -0.1700

Data Index: 1690494 (Open Web Text)

Max Activating Token Index: 754

Text #2

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.2117. Min Act: -0.1700

Data Index: 3111829 (Open Web Text)

Max Activating Token Index: 835

Text #3

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.1553. Min Act: -0.1700

Data Index: 5736151 (Open Web Text)

Max Activating Token Index: 929

Text #4

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0429. Min Act: -0.1700

Data Index: 1109916 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0536. Min Act: -0.1700

Data Index: 4745577 (Open Web Text)

Max Activating Token Index: 679

Text #6

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0095. Min Act: -0.1700

Data Index: 8043700 (Open Web Text)

Max Activating Token Index: 857

Text #7

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0079. Min Act: -0.1700

Data Index: 7020189 (Open Web Text)

Max Activating Token Index: 829

Text #8

Max Range: 4.3239. Min Range: -4.3239

Max Act: 3.9676. Min Act: -0.1700

Data Index: 6708591 (Open Web Text)

Max Activating Token Index: 742

Text #9

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0333. Min Act: -0.1700

Data Index: 7740049 (Open Web Text)

Max Activating Token Index: 622

Text #10

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0119. Min Act: -0.1700

Data Index: 367896 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 4.3239. Min Range: -4.3239

Max Act: 3.9356. Min Act: -0.1700

Data Index: 5312686 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.3239. Min Range: -4.3239

Max Act: 3.9445. Min Act: -0.1700

Data Index: 7277171 (Open Web Text)

Max Activating Token Index: 695

Text #13

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0096. Min Act: -0.1700

Data Index: 8590320 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 4.3239. Min Range: -4.3239

Max Act: 3.9734. Min Act: -0.1700

Data Index: 958747 (Open Web Text)

Max Activating Token Index: 192

Text #15

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0316. Min Act: -0.1700

Data Index: 933009 (Open Web Text)

Max Activating Token Index: 933

Text #16

Max Range: 4.3239. Min Range: -4.3239

Max Act: 4.0598. Min Act: -0.1700

Data Index: 2066294 (Open Web Text)

Max Activating Token Index: 968

Text #17

Max Range: 4.3239. Min Range: -4.3239

Max Act: 3.9248. Min Act: -0.1700

Data Index: 7756959 (Open Web Text)

Max Activating Token Index: 826

Text #18

Max Range: 4.3239. Min Range: -4.3239

Max Act: 3.9225. Min Act: -0.1700

Data Index: 5165787 (Open Web Text)

Max Activating Token Index: 663

Text #19

Max Range: 4.3239. Min Range: -4.3239

Max Act: 3.9417. Min Act: -0.1700

Data Index: 2263290 (Open Web Text)

Max Activating Token Index: 57