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

Dataset: Open Web Text

Neuron 1393 in Layer 4

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: 4.1294. Min Range: -4.1294

Max Act: 4.1294. Min Act: -0.1700

Data Index: 5645322 (Open Web Text)

Max Activating Token Index: 231

Text #1

Max Range: 4.1294. Min Range: -4.1294

Max Act: 4.0684. Min Act: -0.1700

Data Index: 968898 (Open Web Text)

Max Activating Token Index: 131

Text #2

Max Range: 4.1294. Min Range: -4.1294

Max Act: 4.0715. Min Act: -0.1700

Data Index: 2830913 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.9545. Min Act: -0.1700

Data Index: 7858826 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.9420. Min Act: -0.1700

Data Index: 2762933 (Open Web Text)

Max Activating Token Index: 906

Text #5

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.8574. Min Act: -0.1700

Data Index: 8320256 (Open Web Text)

Max Activating Token Index: 813

Text #6

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.8592. Min Act: -0.1700

Data Index: 3196532 (Open Web Text)

Max Activating Token Index: 678

Text #7

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.8630. Min Act: -0.1700

Data Index: 1816971 (Open Web Text)

Max Activating Token Index: 989

Text #8

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.8483. Min Act: -0.1700

Data Index: 8100255 (Open Web Text)

Max Activating Token Index: 339

Text #9

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.8375. Min Act: -0.1700

Data Index: 8600039 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7974. Min Act: -0.1700

Data Index: 8090483 (Open Web Text)

Max Activating Token Index: 278

Text #11

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7969. Min Act: -0.1700

Data Index: 74695 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7872. Min Act: -0.1700

Data Index: 760665 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7993. Min Act: -0.1700

Data Index: 1476650 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7755. Min Act: -0.1700

Data Index: 6985139 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7922. Min Act: -0.1700

Data Index: 7099752 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7704. Min Act: -0.1700

Data Index: 3400189 (Open Web Text)

Max Activating Token Index: 181

Text #17

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7189. Min Act: -0.1700

Data Index: 2058964 (Open Web Text)

Max Activating Token Index: 682

Text #18

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7366. Min Act: -0.1700

Data Index: 3695991 (Open Web Text)

Max Activating Token Index: 332

Text #19

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7642. Min Act: -0.1700

Data Index: 1263716 (Open Web Text)

Max Activating Token Index: 71