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

Dataset: Open Web Text

Neuron 2753 in Layer 6

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: 3.1586. Min Range: -3.1586

Max Act: 3.1586. Min Act: -0.1700

Data Index: 1166652 (Open Web Text)

Max Activating Token Index: 874

Text #1

Max Range: 3.1586. Min Range: -3.1586

Max Act: 3.0395. Min Act: -0.1700

Data Index: 2618074 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.9674. Min Act: -0.1700

Data Index: 3654972 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.9539. Min Act: -0.1700

Data Index: 770661 (Open Web Text)

Max Activating Token Index: 798

Text #4

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8909. Min Act: -0.1700

Data Index: 8607157 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.9134. Min Act: -0.1700

Data Index: 8581613 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.9178. Min Act: -0.1700

Data Index: 4345476 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8912. Min Act: -0.1700

Data Index: 706969 (Open Web Text)

Max Activating Token Index: 768

Text #8

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8570. Min Act: -0.1700

Data Index: 5471145 (Open Web Text)

Max Activating Token Index: 831

Text #9

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8343. Min Act: -0.1700

Data Index: 4903813 (Open Web Text)

Max Activating Token Index: 551

Text #10

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8698. Min Act: -0.1700

Data Index: 4598773 (Open Web Text)

Max Activating Token Index: 289

Text #11

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8180. Min Act: -0.1700

Data Index: 3583683 (Open Web Text)

Max Activating Token Index: 675

Text #12

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8219. Min Act: -0.1700

Data Index: 7304027 (Open Web Text)

Max Activating Token Index: 468

Text #13

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8046. Min Act: -0.1700

Data Index: 4586149 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8124. Min Act: -0.1700

Data Index: 154578 (Open Web Text)

Max Activating Token Index: 203

Text #15

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8298. Min Act: -0.1700

Data Index: 7559366 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.7545. Min Act: -0.1700

Data Index: 4292472 (Open Web Text)

Max Activating Token Index: 972

Text #17

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.7749. Min Act: -0.1700

Data Index: 3359412 (Open Web Text)

Max Activating Token Index: 288

Text #18

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.8018. Min Act: -0.1700

Data Index: 8521821 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 3.1586. Min Range: -3.1586

Max Act: 2.7789. Min Act: -0.1700

Data Index: 5493511 (Open Web Text)

Max Activating Token Index: 84