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

Dataset: Open Web Text

Neuron 95 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: 3.1841. Min Range: -3.1841

Max Act: 3.1841. Min Act: -0.1700

Data Index: 7059771 (Open Web Text)

Max Activating Token Index: 209

Text #1

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.1618. Min Act: -0.1700

Data Index: 3523949 (Open Web Text)

Max Activating Token Index: 305

Text #2

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.1690. Min Act: -0.1700

Data Index: 2257990 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.1135. Min Act: -0.1700

Data Index: 5185460 (Open Web Text)

Max Activating Token Index: 412

Text #4

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.0881. Min Act: -0.1700

Data Index: 3523945 (Open Web Text)

Max Activating Token Index: 435

Text #5

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.0558. Min Act: -0.1700

Data Index: 6842743 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.0539. Min Act: -0.1700

Data Index: 3523934 (Open Web Text)

Max Activating Token Index: 412

Text #7

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.0120. Min Act: -0.1700

Data Index: 3523953 (Open Web Text)

Max Activating Token Index: 486

Text #8

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.0154. Min Act: -0.1700

Data Index: 3523948 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.0098. Min Act: -0.1700

Data Index: 3523952 (Open Web Text)

Max Activating Token Index: 476

Text #10

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.0123. Min Act: -0.1700

Data Index: 3523942 (Open Web Text)

Max Activating Token Index: 249

Text #11

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9943. Min Act: -0.1700

Data Index: 3523941 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9697. Min Act: -0.1700

Data Index: 4822126 (Open Web Text)

Max Activating Token Index: 278

Text #13

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9445. Min Act: -0.1700

Data Index: 6383307 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9667. Min Act: -0.1700

Data Index: 3523950 (Open Web Text)

Max Activating Token Index: 603

Text #15

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9412. Min Act: -0.1700

Data Index: 2630252 (Open Web Text)

Max Activating Token Index: 547

Text #16

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9531. Min Act: -0.1700

Data Index: 1196015 (Open Web Text)

Max Activating Token Index: 254

Text #17

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9417. Min Act: -0.1700

Data Index: 5543866 (Open Web Text)

Max Activating Token Index: 344

Text #18

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9237. Min Act: -0.1700

Data Index: 7600303 (Open Web Text)

Max Activating Token Index: 310

Text #19

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.9266. Min Act: -0.1700

Data Index: 3523946 (Open Web Text)

Max Activating Token Index: 192