Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.9029. Min Act: -0.1700
Data Index: 1103569 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.9029. Min Act: -0.1700
Data Index: 4645976 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.9029. Min Act: -0.1700
Data Index: 3572798 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.9029. Min Act: -0.1700
Data Index: 7849777 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.9029. Min Act: -0.1700
Data Index: 7080525 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.9029. Min Act: -0.1700
Data Index: 6462953 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.9029. Min Act: -0.1700
Data Index: 7045450 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.7779. Min Act: -0.1700
Data Index: 6533115 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6216. Min Act: -0.1700
Data Index: 8299742 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6216. Min Act: -0.1700
Data Index: 1287014 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6216. Min Act: -0.1700
Data Index: 2785714 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6216. Min Act: -0.1700
Data Index: 4937969 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6216. Min Act: -0.1700
Data Index: 4464369 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6216. Min Act: -0.1700
Data Index: 4636759 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6216. Min Act: -0.1700
Data Index: 8114339 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6216. Min Act: -0.1700
Data Index: 8493408 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.4966. Min Act: -0.1700
Data Index: 8106737 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.5278. Min Act: -0.1700
Data Index: 6849167 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.5278. Min Act: -0.1700
Data Index: 1438496 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.4341. Min Act: -0.1700
Data Index: 5547064 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19