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

Dataset: Open Web Text

Neuron 395 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: 3.2690. Min Range: -3.2690

Max Act: 3.2690. Min Act: -0.1700

Data Index: 4417788 (Open Web Text)

Max Activating Token Index: 949

Text #1

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.2232. Min Act: -0.1700

Data Index: 6065262 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1923. Min Act: -0.1700

Data Index: 5146910 (Open Web Text)

Max Activating Token Index: 889

Text #3

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1574. Min Act: -0.1700

Data Index: 503921 (Open Web Text)

Max Activating Token Index: 863

Text #4

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1628. Min Act: -0.1700

Data Index: 8210102 (Open Web Text)

Max Activating Token Index: 904

Text #5

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1047. Min Act: -0.1700

Data Index: 6846859 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1230. Min Act: -0.1700

Data Index: 7529149 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0640. Min Act: -0.1700

Data Index: 7154134 (Open Web Text)

Max Activating Token Index: 889

Text #8

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0917. Min Act: -0.1700

Data Index: 7264537 (Open Web Text)

Max Activating Token Index: 953

Text #9

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0678. Min Act: -0.1700

Data Index: 365594 (Open Web Text)

Max Activating Token Index: 856

Text #10

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0614. Min Act: -0.1700

Data Index: 2585834 (Open Web Text)

Max Activating Token Index: 916

Text #11

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0676. Min Act: -0.1700

Data Index: 6741224 (Open Web Text)

Max Activating Token Index: 921

Text #12

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0291. Min Act: -0.1700

Data Index: 4469896 (Open Web Text)

Max Activating Token Index: 850

Text #13

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0343. Min Act: -0.1700

Data Index: 7355993 (Open Web Text)

Max Activating Token Index: 863

Text #14

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0471. Min Act: -0.1700

Data Index: 45403 (Open Web Text)

Max Activating Token Index: 816

Text #15

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0488. Min Act: -0.1700

Data Index: 6056247 (Open Web Text)

Max Activating Token Index: 888

Text #16

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0173. Min Act: -0.1700

Data Index: 1642778 (Open Web Text)

Max Activating Token Index: 867

Text #17

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0145. Min Act: -0.1700

Data Index: 494869 (Open Web Text)

Max Activating Token Index: 923

Text #18

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0243. Min Act: -0.1700

Data Index: 296857 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.0071. Min Act: -0.1700

Data Index: 976112 (Open Web Text)

Max Activating Token Index: 842