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

Dataset: Open Web Text

Neuron 2675 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: 3.0768. Min Range: -3.0768

Max Act: 3.0768. Min Act: -0.1700

Data Index: 8717651 (Open Web Text)

Max Activating Token Index: 867

Text #1

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9601. Min Act: -0.1700

Data Index: 7367351 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9747. Min Act: -0.1700

Data Index: 5333983 (Open Web Text)

Max Activating Token Index: 995

Text #3

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9422. Min Act: -0.1700

Data Index: 7290037 (Open Web Text)

Max Activating Token Index: 719

Text #4

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9269. Min Act: -0.1700

Data Index: 5370730 (Open Web Text)

Max Activating Token Index: 977

Text #5

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9276. Min Act: -0.1700

Data Index: 4932415 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9226. Min Act: -0.1700

Data Index: 4449793 (Open Web Text)

Max Activating Token Index: 835

Text #7

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9211. Min Act: -0.1700

Data Index: 4036322 (Open Web Text)

Max Activating Token Index: 890

Text #8

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9057. Min Act: -0.1700

Data Index: 8143370 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9299. Min Act: -0.1700

Data Index: 8401632 (Open Web Text)

Max Activating Token Index: 810

Text #10

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.9025. Min Act: -0.1700

Data Index: 2010817 (Open Web Text)

Max Activating Token Index: 464

Text #11

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8923. Min Act: -0.1700

Data Index: 7320571 (Open Web Text)

Max Activating Token Index: 712

Text #12

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8599. Min Act: -0.1700

Data Index: 8812632 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8726. Min Act: -0.1700

Data Index: 5089434 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8729. Min Act: -0.1700

Data Index: 8401635 (Open Web Text)

Max Activating Token Index: 843

Text #15

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8730. Min Act: -0.1700

Data Index: 2289516 (Open Web Text)

Max Activating Token Index: 595

Text #16

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8705. Min Act: -0.1700

Data Index: 7320593 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8712. Min Act: -0.1700

Data Index: 3859155 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8759. Min Act: -0.1700

Data Index: 6228898 (Open Web Text)

Max Activating Token Index: 877

Text #19

Max Range: 3.0768. Min Range: -3.0768

Max Act: 2.8609. Min Act: -0.1700

Data Index: 2289523 (Open Web Text)

Max Activating Token Index: 913