Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.6544. Min Act: -0.1700
Data Index: 4004527 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.6231. Min Act: -0.1700
Data Index: 3388032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.6231. Min Act: -0.1700
Data Index: 6637518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5919. Min Act: -0.1700
Data Index: 3517327 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5919. Min Act: -0.1700
Data Index: 4223085 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5919. Min Act: -0.1700
Data Index: 8714398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5919. Min Act: -0.1700
Data Index: 1148808 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5606. Min Act: -0.1700
Data Index: 1251221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5606. Min Act: -0.1700
Data Index: 5956034 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5606. Min Act: -0.1700
Data Index: 6050566 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5606. Min Act: -0.1700
Data Index: 1821961 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5606. Min Act: -0.1700
Data Index: 544179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5294. Min Act: -0.1700
Data Index: 4964281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5294. Min Act: -0.1700
Data Index: 5801713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5294. Min Act: -0.1700
Data Index: 190328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5294. Min Act: -0.1700
Data Index: 3031810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5294. Min Act: -0.1700
Data Index: 6857068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5294. Min Act: -0.1700
Data Index: 3222812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5294. Min Act: -0.1700
Data Index: 7470247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6544. Min Range: -4.6544
Max Act: 4.5294. Min Act: -0.1700
Data Index: 8328723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19