Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 155 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.9134. Min Act: -0.1700
Data Index: 4361732 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.8821. Min Act: -0.1700
Data Index: 3368217 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.6321. Min Act: -0.1700
Data Index: 6747788 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.5696. Min Act: -0.1700
Data Index: 6012834 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.5696. Min Act: -0.1700
Data Index: 2253375 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.5071. Min Act: -0.1700
Data Index: 6120107 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.5071. Min Act: -0.1700
Data Index: 3269671 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.4759. Min Act: -0.1700
Data Index: 113083 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.4446. Min Act: -0.1700
Data Index: 7824757 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.4134. Min Act: -0.1700
Data Index: 408950 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.3821. Min Act: -0.1700
Data Index: 4622045 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.3509. Min Act: -0.1700
Data Index: 2675350 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.2884. Min Act: -0.1700
Data Index: 410273 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.3196. Min Act: -0.1700
Data Index: 5501510 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.3509. Min Act: -0.1700
Data Index: 5944399 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.2884. Min Act: -0.1700
Data Index: 7684386 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.1946. Min Act: -0.1700
Data Index: 6125628 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.2259. Min Act: -0.1700
Data Index: 6426686 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.2571. Min Act: -0.1700
Data Index: 1078782 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9134. Min Range: -6.9134
Max Act: 6.1946. Min Act: -0.1700
Data Index: 3931165 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19