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

Dataset: Open Web Text

Neuron 1025 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: 3.0335. Min Range: -3.0335

Max Act: 3.0335. Min Act: -0.1700

Data Index: 181536 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 3.0335. Min Range: -3.0335

Max Act: 3.0031. Min Act: -0.1700

Data Index: 3360385 (Open Web Text)

Max Activating Token Index: 758

Text #2

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.9566. Min Act: -0.1700

Data Index: 181537 (Open Web Text)

Max Activating Token Index: 147

Text #3

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.9352. Min Act: -0.1700

Data Index: 4680800 (Open Web Text)

Max Activating Token Index: 998

Text #4

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.9249. Min Act: -0.1700

Data Index: 4840102 (Open Web Text)

Max Activating Token Index: 301

Text #5

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8992. Min Act: -0.1700

Data Index: 6802234 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.9087. Min Act: -0.1700

Data Index: 1385213 (Open Web Text)

Max Activating Token Index: 945

Text #7

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8885. Min Act: -0.1700

Data Index: 5280516 (Open Web Text)

Max Activating Token Index: 969

Text #8

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8546. Min Act: -0.1700

Data Index: 7562376 (Open Web Text)

Max Activating Token Index: 655

Text #9

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8846. Min Act: -0.1700

Data Index: 6230427 (Open Web Text)

Max Activating Token Index: 769

Text #10

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8775. Min Act: -0.1700

Data Index: 694901 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8585. Min Act: -0.1700

Data Index: 8606278 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8707. Min Act: -0.1700

Data Index: 5405785 (Open Web Text)

Max Activating Token Index: 981

Text #13

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8716. Min Act: -0.1700

Data Index: 6115914 (Open Web Text)

Max Activating Token Index: 459

Text #14

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8721. Min Act: -0.1700

Data Index: 1621194 (Open Web Text)

Max Activating Token Index: 991

Text #15

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8409. Min Act: -0.1700

Data Index: 3190646 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8564. Min Act: -0.1700

Data Index: 2330143 (Open Web Text)

Max Activating Token Index: 810

Text #17

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8264. Min Act: -0.1700

Data Index: 815421 (Open Web Text)

Max Activating Token Index: 777

Text #18

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8342. Min Act: -0.1700

Data Index: 663963 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 3.0335. Min Range: -3.0335

Max Act: 2.8131. Min Act: -0.1700

Data Index: 623255 (Open Web Text)

Max Activating Token Index: 960