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

Dataset: Open Web Text

Neuron 2274 in Layer 1

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: 1.1642. Min Range: -1.1642

Max Act: 1.1642. Min Act: -0.1700

Data Index: 781068 (Open Web Text)

Max Activating Token Index: 945

Text #1

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.1093. Min Act: -0.1700

Data Index: 5693889 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0896. Min Act: -0.1700

Data Index: 4552371 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0626. Min Act: -0.1700

Data Index: 7817927 (Open Web Text)

Max Activating Token Index: 937

Text #4

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0659. Min Act: -0.1700

Data Index: 3885718 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0587. Min Act: -0.1700

Data Index: 7882637 (Open Web Text)

Max Activating Token Index: 944

Text #6

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0429. Min Act: -0.1700

Data Index: 7421614 (Open Web Text)

Max Activating Token Index: 958

Text #7

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0195. Min Act: -0.1700

Data Index: 7059819 (Open Web Text)

Max Activating Token Index: 912

Text #8

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0257. Min Act: -0.1700

Data Index: 3876947 (Open Web Text)

Max Activating Token Index: 938

Text #9

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0197. Min Act: -0.1700

Data Index: 6401505 (Open Web Text)

Max Activating Token Index: 949

Text #10

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0138. Min Act: -0.1700

Data Index: 5023913 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0191. Min Act: -0.1700

Data Index: 3188600 (Open Web Text)

Max Activating Token Index: 947

Text #12

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0126. Min Act: -0.1700

Data Index: 8116908 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0204. Min Act: -0.1700

Data Index: 524387 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0210. Min Act: -0.1700

Data Index: 5845696 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0078. Min Act: -0.1700

Data Index: 4514622 (Open Web Text)

Max Activating Token Index: 905

Text #16

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0051. Min Act: -0.1700

Data Index: 1996020 (Open Web Text)

Max Activating Token Index: 925

Text #17

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0025. Min Act: -0.1700

Data Index: 3543216 (Open Web Text)

Max Activating Token Index: 920

Text #18

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9977. Min Act: -0.1700

Data Index: 7997691 (Open Web Text)

Max Activating Token Index: 922

Text #19

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9965. Min Act: -0.1700

Data Index: 5886350 (Open Web Text)

Max Activating Token Index: 944