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

Dataset: Open Web Text

Neuron 2179 in Layer 3

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: 0.6390. Min Range: -0.6390

Max Act: 0.6390. Min Act: -0.1700

Data Index: 7820983 (Open Web Text)

Max Activating Token Index: 854

Text #1

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.6081. Min Act: -0.1700

Data Index: 4286910 (Open Web Text)

Max Activating Token Index: 881

Text #2

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.6319. Min Act: -0.1700

Data Index: 4373705 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5963. Min Act: -0.1700

Data Index: 4700962 (Open Web Text)

Max Activating Token Index: 895

Text #4

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5857. Min Act: -0.1700

Data Index: 5456433 (Open Web Text)

Max Activating Token Index: 890

Text #5

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.6030. Min Act: -0.1700

Data Index: 310490 (Open Web Text)

Max Activating Token Index: 866

Text #6

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5927. Min Act: -0.1700

Data Index: 3340186 (Open Web Text)

Max Activating Token Index: 924

Text #7

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5825. Min Act: -0.1700

Data Index: 2005090 (Open Web Text)

Max Activating Token Index: 860

Text #8

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5988. Min Act: -0.1700

Data Index: 6495017 (Open Web Text)

Max Activating Token Index: 822

Text #9

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5821. Min Act: -0.1700

Data Index: 5823487 (Open Web Text)

Max Activating Token Index: 908

Text #10

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5920. Min Act: -0.1700

Data Index: 7506849 (Open Web Text)

Max Activating Token Index: 886

Text #11

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5682. Min Act: -0.1700

Data Index: 3201421 (Open Web Text)

Max Activating Token Index: 847

Text #12

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5666. Min Act: -0.1700

Data Index: 2955332 (Open Web Text)

Max Activating Token Index: 939

Text #13

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5877. Min Act: -0.1700

Data Index: 4938583 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5794. Min Act: -0.1700

Data Index: 6169058 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5506. Min Act: -0.1700

Data Index: 6316338 (Open Web Text)

Max Activating Token Index: 840

Text #16

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5552. Min Act: -0.1700

Data Index: 47651 (Open Web Text)

Max Activating Token Index: 873

Text #17

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5538. Min Act: -0.1700

Data Index: 3227705 (Open Web Text)

Max Activating Token Index: 904

Text #18

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5606. Min Act: -0.1700

Data Index: 1462104 (Open Web Text)

Max Activating Token Index: 917

Text #19

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.5499. Min Act: -0.1700

Data Index: 5082379 (Open Web Text)

Max Activating Token Index: 1023