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

Dataset: Open Web Text

Neuron 502 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: 3.8568. Min Range: -3.8568

Max Act: 3.8507. Min Act: -0.1700

Data Index: 730937 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.8568. Min Act: -0.1700

Data Index: 7277558 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.7628. Min Act: -0.1700

Data Index: 917708 (Open Web Text)

Max Activating Token Index: 442

Text #3

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.7288. Min Act: -0.1700

Data Index: 4029404 (Open Web Text)

Max Activating Token Index: 974

Text #4

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.7401. Min Act: -0.1700

Data Index: 2658993 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.7402. Min Act: -0.1700

Data Index: 8333464 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.7184. Min Act: -0.1700

Data Index: 6132978 (Open Web Text)

Max Activating Token Index: 614

Text #7

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6912. Min Act: -0.1700

Data Index: 7707179 (Open Web Text)

Max Activating Token Index: 983

Text #8

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6555. Min Act: -0.1700

Data Index: 3892798 (Open Web Text)

Max Activating Token Index: 201

Text #9

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6714. Min Act: -0.1700

Data Index: 2324083 (Open Web Text)

Max Activating Token Index: 121

Text #10

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6756. Min Act: -0.1700

Data Index: 8461496 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.7075. Min Act: -0.1700

Data Index: 8385325 (Open Web Text)

Max Activating Token Index: 171

Text #12

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6641. Min Act: -0.1700

Data Index: 3540655 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6770. Min Act: -0.1700

Data Index: 5485661 (Open Web Text)

Max Activating Token Index: 619

Text #14

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6770. Min Act: -0.1700

Data Index: 190535 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6963. Min Act: -0.1700

Data Index: 4688341 (Open Web Text)

Max Activating Token Index: 626

Text #16

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6615. Min Act: -0.1700

Data Index: 603929 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6787. Min Act: -0.1700

Data Index: 7671826 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6483. Min Act: -0.1700

Data Index: 6470670 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 3.8568. Min Range: -3.8568

Max Act: 3.6389. Min Act: -0.1700

Data Index: 1738646 (Open Web Text)

Max Activating Token Index: 328