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

Dataset: Open Web Text

Neuron 798 in Layer 2

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: 4.6739. Min Range: -4.6739

Max Act: 4.6739. Min Act: -0.1700

Data Index: 1533243 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.6273. Min Act: -0.1700

Data Index: 5390752 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.5677. Min Act: -0.1700

Data Index: 7758123 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.5032. Min Act: -0.1700

Data Index: 2750304 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.5419. Min Act: -0.1700

Data Index: 4280857 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.5055. Min Act: -0.1700

Data Index: 57809 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.4761. Min Act: -0.1700

Data Index: 6944782 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.4769. Min Act: -0.1700

Data Index: 6194944 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3971. Min Act: -0.1700

Data Index: 2626478 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.4064. Min Act: -0.1700

Data Index: 2901290 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.4112. Min Act: -0.1700

Data Index: 8619251 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3753. Min Act: -0.1700

Data Index: 1919354 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3709. Min Act: -0.1700

Data Index: 678276 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3772. Min Act: -0.1700

Data Index: 8100154 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3874. Min Act: -0.1700

Data Index: 429616 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3107. Min Act: -0.1700

Data Index: 5108209 (Open Web Text)

Max Activating Token Index: 276

Text #16

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3426. Min Act: -0.1700

Data Index: 459005 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3543. Min Act: -0.1700

Data Index: 504726 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.3053. Min Act: -0.1700

Data Index: 132910 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.6739. Min Range: -4.6739

Max Act: 4.2964. Min Act: -0.1700

Data Index: 3205950 (Open Web Text)

Max Activating Token Index: 19