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

Dataset: Open Web Text

Neuron 2580 in Layer 1

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: 2.1111. Min Range: -2.1111

Max Act: 2.1111. Min Act: -0.1700

Data Index: 5798948 (Open Web Text)

Max Activating Token Index: 668

Text #1

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0914. Min Act: -0.1700

Data Index: 7953378 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0775. Min Act: -0.1700

Data Index: 3699676 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0688. Min Act: -0.1700

Data Index: 606729 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0149. Min Act: -0.1700

Data Index: 8538727 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0121. Min Act: -0.1700

Data Index: 8264691 (Open Web Text)

Max Activating Token Index: 563

Text #6

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0222. Min Act: -0.1700

Data Index: 4138794 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9998. Min Act: -0.1700

Data Index: 6448042 (Open Web Text)

Max Activating Token Index: 371

Text #8

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0101. Min Act: -0.1700

Data Index: 4179092 (Open Web Text)

Max Activating Token Index: 381

Text #9

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0028. Min Act: -0.1700

Data Index: 5353729 (Open Web Text)

Max Activating Token Index: 650

Text #10

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9964. Min Act: -0.1700

Data Index: 853715 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 2.1111. Min Range: -2.1111

Max Act: 2.0117. Min Act: -0.1700

Data Index: 5373536 (Open Web Text)

Max Activating Token Index: 420

Text #12

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9900. Min Act: -0.1700

Data Index: 4411920 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9919. Min Act: -0.1700

Data Index: 2147391 (Open Web Text)

Max Activating Token Index: 415

Text #14

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9860. Min Act: -0.1700

Data Index: 7356466 (Open Web Text)

Max Activating Token Index: 219

Text #15

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9896. Min Act: -0.1700

Data Index: 8322613 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9840. Min Act: -0.1700

Data Index: 3153816 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9835. Min Act: -0.1700

Data Index: 8777599 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9904. Min Act: -0.1700

Data Index: 8564077 (Open Web Text)

Max Activating Token Index: 268

Text #19

Max Range: 2.1111. Min Range: -2.1111

Max Act: 1.9901. Min Act: -0.1700

Data Index: 7394639 (Open Web Text)

Max Activating Token Index: 115