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

Dataset: Open Web Text

Neuron 2046 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: 1.9413. Min Range: -1.9413

Max Act: 1.9413. Min Act: -0.0746

Data Index: 7569117 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.8034. Min Act: -0.1035

Data Index: 5425261 (Open Web Text)

Max Activating Token Index: 934

Text #2

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.8001. Min Act: -0.1418

Data Index: 5347540 (Open Web Text)

Max Activating Token Index: 812

Text #3

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7754. Min Act: -0.0146

Data Index: 3704388 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7675. Min Act: -0.0505

Data Index: 4052020 (Open Web Text)

Max Activating Token Index: 252

Text #5

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7666. Min Act: 0.0174

Data Index: 948585 (Open Web Text)

Max Activating Token Index: 852

Text #6

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7609. Min Act: -0.0826

Data Index: 5425259 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7525. Min Act: -0.1552

Data Index: 2971295 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7576. Min Act: -0.0901

Data Index: 3430923 (Open Web Text)

Max Activating Token Index: 859

Text #9

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7464. Min Act: -0.0519

Data Index: 3108676 (Open Web Text)

Max Activating Token Index: 483

Text #10

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7405. Min Act: -0.1089

Data Index: 3704398 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7098. Min Act: -0.0797

Data Index: 5425260 (Open Web Text)

Max Activating Token Index: 977

Text #12

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7176. Min Act: -0.0543

Data Index: 186803 (Open Web Text)

Max Activating Token Index: 841

Text #13

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7169. Min Act: -0.1139

Data Index: 4903842 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7123. Min Act: -0.1516

Data Index: 5767794 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7038. Min Act: -0.1099

Data Index: 186808 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7084. Min Act: -0.0341

Data Index: 3166015 (Open Web Text)

Max Activating Token Index: 530

Text #17

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7109. Min Act: -0.0967

Data Index: 6605446 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7120. Min Act: -0.0976

Data Index: 755098 (Open Web Text)

Max Activating Token Index: 480

Text #19

Max Range: 1.9413. Min Range: -1.9413

Max Act: 1.7030. Min Act: -0.0859

Data Index: 4907897 (Open Web Text)

Max Activating Token Index: 432