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

Dataset: Open Web Text

Neuron 2910 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: 4.4546. Min Range: -4.4546

Max Act: 4.4546. Min Act: -0.1700

Data Index: 1212624 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.3643. Min Act: -0.1700

Data Index: 4194604 (Open Web Text)

Max Activating Token Index: 710

Text #2

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.2605. Min Act: -0.1700

Data Index: 1040576 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.1532. Min Act: -0.1700

Data Index: 3914693 (Open Web Text)

Max Activating Token Index: 597

Text #4

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.1077. Min Act: -0.1700

Data Index: 1068284 (Open Web Text)

Max Activating Token Index: 631

Text #5

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.1393. Min Act: -0.1700

Data Index: 2706663 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.1158. Min Act: -0.1700

Data Index: 5645810 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0745. Min Act: -0.1700

Data Index: 3706085 (Open Web Text)

Max Activating Token Index: 239

Text #8

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.1102. Min Act: -0.1700

Data Index: 4896747 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0762. Min Act: -0.1700

Data Index: 8138615 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0527. Min Act: -0.1700

Data Index: 5291205 (Open Web Text)

Max Activating Token Index: 289

Text #11

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0669. Min Act: -0.1700

Data Index: 3714585 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0519. Min Act: -0.1700

Data Index: 6454689 (Open Web Text)

Max Activating Token Index: 327

Text #13

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0157. Min Act: -0.1700

Data Index: 4072041 (Open Web Text)

Max Activating Token Index: 253

Text #14

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0102. Min Act: -0.1700

Data Index: 8476193 (Open Web Text)

Max Activating Token Index: 932

Text #15

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0534. Min Act: -0.1700

Data Index: 521346 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0112. Min Act: -0.1700

Data Index: 6902597 (Open Web Text)

Max Activating Token Index: 692

Text #17

Max Range: 4.4546. Min Range: -4.4546

Max Act: 3.9830. Min Act: -0.1700

Data Index: 45938 (Open Web Text)

Max Activating Token Index: 964

Text #18

Max Range: 4.4546. Min Range: -4.4546

Max Act: 3.9816. Min Act: -0.1700

Data Index: 5593365 (Open Web Text)

Max Activating Token Index: 863

Text #19

Max Range: 4.4546. Min Range: -4.4546

Max Act: 4.0316. Min Act: -0.1700

Data Index: 3949762 (Open Web Text)

Max Activating Token Index: 515