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

Dataset: Open Web Text

Neuron 1079 in Layer 2

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: 3.1559. Min Range: -3.1559

Max Act: 3.1559. Min Act: -0.1700

Data Index: 1402779 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.1559. Min Range: -3.1559

Max Act: 3.0684. Min Act: -0.1700

Data Index: 5357960 (Open Web Text)

Max Activating Token Index: 529

Text #2

Max Range: 3.1559. Min Range: -3.1559

Max Act: 3.0560. Min Act: -0.1700

Data Index: 1943427 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 3.1559. Min Range: -3.1559

Max Act: 3.0392. Min Act: -0.1700

Data Index: 1241675 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 3.1559. Min Range: -3.1559

Max Act: 3.0508. Min Act: -0.1700

Data Index: 6569905 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 3.1559. Min Range: -3.1559

Max Act: 3.0270. Min Act: -0.1700

Data Index: 7557281 (Open Web Text)

Max Activating Token Index: 938

Text #6

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9963. Min Act: -0.1700

Data Index: 4188810 (Open Web Text)

Max Activating Token Index: 524

Text #7

Max Range: 3.1559. Min Range: -3.1559

Max Act: 3.0132. Min Act: -0.1700

Data Index: 4586046 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9937. Min Act: -0.1700

Data Index: 2701771 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9939. Min Act: -0.1700

Data Index: 150879 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 3.1559. Min Range: -3.1559

Max Act: 3.0044. Min Act: -0.1700

Data Index: 4434517 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9721. Min Act: -0.1700

Data Index: 637068 (Open Web Text)

Max Activating Token Index: 834

Text #12

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9922. Min Act: -0.1700

Data Index: 4169249 (Open Web Text)

Max Activating Token Index: 739

Text #13

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9673. Min Act: -0.1700

Data Index: 759893 (Open Web Text)

Max Activating Token Index: 833

Text #14

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9531. Min Act: -0.1700

Data Index: 7944290 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9283. Min Act: -0.1700

Data Index: 3467143 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9314. Min Act: -0.1700

Data Index: 1885024 (Open Web Text)

Max Activating Token Index: 806

Text #17

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9240. Min Act: -0.1700

Data Index: 420939 (Open Web Text)

Max Activating Token Index: 772

Text #18

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9316. Min Act: -0.1700

Data Index: 4828485 (Open Web Text)

Max Activating Token Index: 840

Text #19

Max Range: 3.1559. Min Range: -3.1559

Max Act: 2.9192. Min Act: -0.1700

Data Index: 2544463 (Open Web Text)

Max Activating Token Index: 192