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

Dataset: Open Web Text

Neuron 1436 in Layer 2

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: 1.8462. Min Range: -1.8462

Max Act: 1.8462. Min Act: -0.1700

Data Index: 1501429 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.8282. Min Act: -0.1700

Data Index: 155695 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.8173. Min Act: -0.1700

Data Index: 4825870 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.8074. Min Act: -0.1700

Data Index: 6561233 (Open Web Text)

Max Activating Token Index: 192

Text #4

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7950. Min Act: -0.1699

Data Index: 858949 (Open Web Text)

Max Activating Token Index: 561

Text #5

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7916. Min Act: -0.1700

Data Index: 7586732 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7774. Min Act: -0.1700

Data Index: 2478012 (Open Web Text)

Max Activating Token Index: 124

Text #7

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7720. Min Act: -0.1700

Data Index: 7228207 (Open Web Text)

Max Activating Token Index: 994

Text #8

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7802. Min Act: -0.1700

Data Index: 401014 (Open Web Text)

Max Activating Token Index: 357

Text #9

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7735. Min Act: -0.1700

Data Index: 4760368 (Open Web Text)

Max Activating Token Index: 371

Text #10

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7919. Min Act: -0.1700

Data Index: 2574421 (Open Web Text)

Max Activating Token Index: 807

Text #11

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7842. Min Act: -0.1700

Data Index: 5962434 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7828. Min Act: -0.1700

Data Index: 2894940 (Open Web Text)

Max Activating Token Index: 1008

Text #13

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7780. Min Act: -0.1700

Data Index: 2971251 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7631. Min Act: -0.1700

Data Index: 5210966 (Open Web Text)

Max Activating Token Index: 797

Text #15

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7674. Min Act: -0.1700

Data Index: 4960555 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7735. Min Act: -0.1700

Data Index: 3523266 (Open Web Text)

Max Activating Token Index: 330

Text #17

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7624. Min Act: -0.1700

Data Index: 6229340 (Open Web Text)

Max Activating Token Index: 313

Text #18

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7674. Min Act: -0.1700

Data Index: 7681598 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7703. Min Act: -0.1700

Data Index: 769695 (Open Web Text)

Max Activating Token Index: 759