Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.6778. Min Act: -0.1700
Data Index: 5839858 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.6778. Min Act: -0.1700
Data Index: 8459610 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5839. Min Act: -0.1700
Data Index: 400822 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5682. Min Act: -0.1700
Data Index: 4170154 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5682. Min Act: -0.1700
Data Index: 1449801 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5526. Min Act: -0.1700
Data Index: 1692048 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5526. Min Act: -0.1700
Data Index: 6090039 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5212. Min Act: -0.1700
Data Index: 1575420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5212. Min Act: -0.1700
Data Index: 6275990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5212. Min Act: -0.1700
Data Index: 2459122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5369. Min Act: -0.1700
Data Index: 6756201 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5212. Min Act: -0.1700
Data Index: 1170749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5212. Min Act: -0.1700
Data Index: 8101314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5056. Min Act: -0.1700
Data Index: 3801169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.4899. Min Act: -0.1700
Data Index: 8132236 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5056. Min Act: -0.1700
Data Index: 4417553 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.4899. Min Act: -0.1700
Data Index: 2699529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.5056. Min Act: -0.1700
Data Index: 7389150 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.4899. Min Act: -0.1700
Data Index: 8041896 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6778. Min Range: -3.6778
Max Act: 3.4899. Min Act: -0.1700
Data Index: 3611112 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19