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

Dataset: Open Web Text

Neuron 2651 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: 4.0680. Min Range: -4.0680

Max Act: 4.0680. Min Act: -0.1700

Data Index: 1626675 (Open Web Text)

Max Activating Token Index: 687

Text #1

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.9608. Min Act: -0.1700

Data Index: 2091340 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.9362. Min Act: -0.1700

Data Index: 7598704 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.9114. Min Act: -0.1700

Data Index: 1626679 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8789. Min Act: -0.1700

Data Index: 1553221 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8604. Min Act: -0.1700

Data Index: 3026133 (Open Web Text)

Max Activating Token Index: 437

Text #6

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8992. Min Act: -0.1700

Data Index: 1626682 (Open Web Text)

Max Activating Token Index: 249

Text #7

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8437. Min Act: -0.1700

Data Index: 5110065 (Open Web Text)

Max Activating Token Index: 566

Text #8

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8277. Min Act: -0.1700

Data Index: 1626712 (Open Web Text)

Max Activating Token Index: 674

Text #9

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8546. Min Act: -0.1700

Data Index: 7470206 (Open Web Text)

Max Activating Token Index: 700

Text #10

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8397. Min Act: -0.1700

Data Index: 1626693 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8188. Min Act: -0.1700

Data Index: 2837387 (Open Web Text)

Max Activating Token Index: 875

Text #12

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8202. Min Act: -0.1700

Data Index: 2498495 (Open Web Text)

Max Activating Token Index: 606

Text #13

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8009. Min Act: -0.1700

Data Index: 6336906 (Open Web Text)

Max Activating Token Index: 497

Text #14

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8030. Min Act: -0.1700

Data Index: 1626678 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.7953. Min Act: -0.1700

Data Index: 5056174 (Open Web Text)

Max Activating Token Index: 405

Text #16

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8106. Min Act: -0.1700

Data Index: 1626677 (Open Web Text)

Max Activating Token Index: 29

Text #17

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.8184. Min Act: -0.1700

Data Index: 1626699 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.7564. Min Act: -0.1700

Data Index: 1626710 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 4.0680. Min Range: -4.0680

Max Act: 3.7844. Min Act: -0.1700

Data Index: 4866417 (Open Web Text)

Max Activating Token Index: 468