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

Dataset: Open Web Text

Neuron 1467 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: 5.8761. Min Range: -5.8761

Max Act: 5.8761. Min Act: -0.1700

Data Index: 1481765 (Open Web Text)

Max Activating Token Index: 555

Text #1

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.8001. Min Act: -0.1700

Data Index: 5814373 (Open Web Text)

Max Activating Token Index: 909

Text #2

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6898. Min Act: -0.1700

Data Index: 7736030 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.7124. Min Act: -0.1700

Data Index: 696602 (Open Web Text)

Max Activating Token Index: 296

Text #4

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6695. Min Act: -0.1700

Data Index: 6812395 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6731. Min Act: -0.1700

Data Index: 1545896 (Open Web Text)

Max Activating Token Index: 144

Text #6

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6642. Min Act: -0.1700

Data Index: 3671782 (Open Web Text)

Max Activating Token Index: 646

Text #7

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6876. Min Act: -0.1700

Data Index: 8449276 (Open Web Text)

Max Activating Token Index: 541

Text #8

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6755. Min Act: -0.1700

Data Index: 7433002 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6510. Min Act: -0.1700

Data Index: 7485823 (Open Web Text)

Max Activating Token Index: 759

Text #10

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6544. Min Act: -0.1700

Data Index: 1492672 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6607. Min Act: -0.1700

Data Index: 1661107 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6148. Min Act: -0.1700

Data Index: 8512097 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6481. Min Act: -0.1700

Data Index: 3102484 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6072. Min Act: -0.1700

Data Index: 7495740 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6184. Min Act: -0.1700

Data Index: 7535013 (Open Web Text)

Max Activating Token Index: 131

Text #16

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6399. Min Act: -0.1700

Data Index: 216443 (Open Web Text)

Max Activating Token Index: 439

Text #17

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6039. Min Act: -0.1700

Data Index: 571964 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.5848. Min Act: -0.1700

Data Index: 2452994 (Open Web Text)

Max Activating Token Index: 910

Text #19

Max Range: 5.8761. Min Range: -5.8761

Max Act: 5.6492. Min Act: -0.1700

Data Index: 4108937 (Open Web Text)

Max Activating Token Index: 726