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

Dataset: Open Web Text

Neuron 762 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: 3.1139. Min Range: -3.1139

Max Act: 3.1098. Min Act: -0.1700

Data Index: 6874066 (Open Web Text)

Max Activating Token Index: 879

Text #1

Max Range: 3.1139. Min Range: -3.1139

Max Act: 3.1139. Min Act: -0.1700

Data Index: 4465727 (Open Web Text)

Max Activating Token Index: 356

Text #2

Max Range: 3.1139. Min Range: -3.1139

Max Act: 3.0522. Min Act: -0.1700

Data Index: 2793598 (Open Web Text)

Max Activating Token Index: 553

Text #3

Max Range: 3.1139. Min Range: -3.1139

Max Act: 3.0420. Min Act: -0.1700

Data Index: 454586 (Open Web Text)

Max Activating Token Index: 757

Text #4

Max Range: 3.1139. Min Range: -3.1139

Max Act: 3.0069. Min Act: -0.1700

Data Index: 3334385 (Open Web Text)

Max Activating Token Index: 214

Text #5

Max Range: 3.1139. Min Range: -3.1139

Max Act: 3.0075. Min Act: -0.1700

Data Index: 5424542 (Open Web Text)

Max Activating Token Index: 797

Text #6

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.9971. Min Act: -0.1700

Data Index: 5969025 (Open Web Text)

Max Activating Token Index: 943

Text #7

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.9376. Min Act: -0.1700

Data Index: 97942 (Open Web Text)

Max Activating Token Index: 272

Text #8

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.9140. Min Act: -0.1700

Data Index: 6107666 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.9185. Min Act: -0.1700

Data Index: 1004891 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.9141. Min Act: -0.1700

Data Index: 3409595 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.9061. Min Act: -0.1700

Data Index: 2671084 (Open Web Text)

Max Activating Token Index: 690

Text #12

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.9275. Min Act: -0.1700

Data Index: 8683507 (Open Web Text)

Max Activating Token Index: 617

Text #13

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.8916. Min Act: -0.1700

Data Index: 416977 (Open Web Text)

Max Activating Token Index: 659

Text #14

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.9038. Min Act: -0.1700

Data Index: 7786108 (Open Web Text)

Max Activating Token Index: 933

Text #15

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.8727. Min Act: -0.1700

Data Index: 58453 (Open Web Text)

Max Activating Token Index: 275

Text #16

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.8960. Min Act: -0.1700

Data Index: 5689229 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.8857. Min Act: -0.1700

Data Index: 7443229 (Open Web Text)

Max Activating Token Index: 475

Text #18

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.8667. Min Act: -0.1700

Data Index: 5989361 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.8908. Min Act: -0.1700

Data Index: 5543501 (Open Web Text)

Max Activating Token Index: 712