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

Dataset: Open Web Text

Neuron 1253 in Layer 6

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: 4.1130. Min Range: -4.1130

Max Act: 4.1130. Min Act: -0.1700

Data Index: 1984172 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 4.1130. Min Range: -4.1130

Max Act: 4.0559. Min Act: -0.1700

Data Index: 5676641 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 4.1130. Min Range: -4.1130

Max Act: 4.0549. Min Act: -0.1700

Data Index: 2601692 (Open Web Text)

Max Activating Token Index: 303

Text #3

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8690. Min Act: -0.1700

Data Index: 7980438 (Open Web Text)

Max Activating Token Index: 626

Text #4

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.9014. Min Act: -0.1700

Data Index: 6763690 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8857. Min Act: -0.1700

Data Index: 1086256 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8365. Min Act: -0.1700

Data Index: 1632450 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8670. Min Act: -0.1700

Data Index: 2282558 (Open Web Text)

Max Activating Token Index: 335

Text #8

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8429. Min Act: -0.1700

Data Index: 4770585 (Open Web Text)

Max Activating Token Index: 244

Text #9

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8142. Min Act: -0.1700

Data Index: 4298030 (Open Web Text)

Max Activating Token Index: 97

Text #10

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.7891. Min Act: -0.1700

Data Index: 5203413 (Open Web Text)

Max Activating Token Index: 257

Text #11

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.7657. Min Act: -0.1700

Data Index: 1038180 (Open Web Text)

Max Activating Token Index: 606

Text #12

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8091. Min Act: -0.1700

Data Index: 477736 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8092. Min Act: -0.1700

Data Index: 4548974 (Open Web Text)

Max Activating Token Index: 768

Text #14

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.7803. Min Act: -0.1700

Data Index: 5079739 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8072. Min Act: -0.1700

Data Index: 3828407 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.7606. Min Act: -0.1700

Data Index: 891236 (Open Web Text)

Max Activating Token Index: 1004

Text #17

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.7805. Min Act: -0.1700

Data Index: 7557326 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8068. Min Act: -0.1700

Data Index: 685375 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.7346. Min Act: -0.1700

Data Index: 3548775 (Open Web Text)

Max Activating Token Index: 389