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

Dataset: Open Web Text

Neuron 2273 in Layer 5

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: 3.7770. Min Range: -3.7770

Max Act: 3.7770. Min Act: -0.1700

Data Index: 5648294 (Open Web Text)

Max Activating Token Index: 153

Text #1

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.7271. Min Act: -0.1700

Data Index: 6081890 (Open Web Text)

Max Activating Token Index: 769

Text #2

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.7064. Min Act: -0.1700

Data Index: 20979 (Open Web Text)

Max Activating Token Index: 381

Text #3

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.6909. Min Act: -0.1700

Data Index: 596879 (Open Web Text)

Max Activating Token Index: 463

Text #4

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.7119. Min Act: -0.1700

Data Index: 3178136 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.7007. Min Act: -0.1700

Data Index: 2445065 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.7264. Min Act: -0.1700

Data Index: 5959897 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.6799. Min Act: -0.1700

Data Index: 7130477 (Open Web Text)

Max Activating Token Index: 262

Text #8

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.6770. Min Act: -0.1700

Data Index: 6964276 (Open Web Text)

Max Activating Token Index: 269

Text #9

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.6568. Min Act: -0.1700

Data Index: 4985623 (Open Web Text)

Max Activating Token Index: 876

Text #10

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.6192. Min Act: -0.1700

Data Index: 20205 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.5981. Min Act: -0.1700

Data Index: 6280679 (Open Web Text)

Max Activating Token Index: 874

Text #12

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.6036. Min Act: -0.1700

Data Index: 8042496 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.6078. Min Act: -0.1700

Data Index: 5961725 (Open Web Text)

Max Activating Token Index: 662

Text #14

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.6063. Min Act: -0.1700

Data Index: 1005357 (Open Web Text)

Max Activating Token Index: 315

Text #15

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.5830. Min Act: -0.1700

Data Index: 4414321 (Open Web Text)

Max Activating Token Index: 243

Text #16

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.5668. Min Act: -0.1700

Data Index: 5401846 (Open Web Text)

Max Activating Token Index: 723

Text #17

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.5650. Min Act: -0.1700

Data Index: 6815757 (Open Web Text)

Max Activating Token Index: 38

Text #18

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.5622. Min Act: -0.1700

Data Index: 4995395 (Open Web Text)

Max Activating Token Index: 797

Text #19

Max Range: 3.7770. Min Range: -3.7770

Max Act: 3.5585. Min Act: -0.1700

Data Index: 6688776 (Open Web Text)

Max Activating Token Index: 409