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

Dataset: Open Web Text

Neuron 1752 in Layer 5

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: 1.6712. Min Range: -1.6712

Max Act: 1.6712. Min Act: -0.1700

Data Index: 4771710 (Open Web Text)

Max Activating Token Index: 993

Text #1

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.6138. Min Act: -0.1700

Data Index: 5975300 (Open Web Text)

Max Activating Token Index: 707

Text #2

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.6029. Min Act: -0.1691

Data Index: 2558647 (Open Web Text)

Max Activating Token Index: 565

Text #3

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.6247. Min Act: -0.1700

Data Index: 7709971 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.6286. Min Act: -0.1700

Data Index: 2331755 (Open Web Text)

Max Activating Token Index: 800

Text #5

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.5412. Min Act: -0.1700

Data Index: 8367870 (Open Web Text)

Max Activating Token Index: 751

Text #6

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.5379. Min Act: -0.1700

Data Index: 7077299 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.5362. Min Act: -0.1700

Data Index: 2584337 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.5203. Min Act: -0.1691

Data Index: 2278978 (Open Web Text)

Max Activating Token Index: 1009

Text #9

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4988. Min Act: -0.1700

Data Index: 5127882 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4898. Min Act: -0.1700

Data Index: 1418253 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4975. Min Act: -0.1700

Data Index: 3923915 (Open Web Text)

Max Activating Token Index: 659

Text #12

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4847. Min Act: -0.1654

Data Index: 2278968 (Open Web Text)

Max Activating Token Index: 971

Text #13

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4901. Min Act: -0.1700

Data Index: 5355170 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.5030. Min Act: -0.1630

Data Index: 501820 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4853. Min Act: -0.1700

Data Index: 7565501 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4845. Min Act: -0.1694

Data Index: 2604764 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4762. Min Act: -0.1666

Data Index: 2278983 (Open Web Text)

Max Activating Token Index: 992

Text #18

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4795. Min Act: -0.1700

Data Index: 1660863 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4644. Min Act: -0.1700

Data Index: 7280778 (Open Web Text)

Max Activating Token Index: 1017