Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 540 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.6950. Min Act: -0.1700
Data Index: 4129961 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.7110. Min Act: -0.1700
Data Index: 7973748 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.6790. Min Act: -0.1700
Data Index: 3974310 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.6309. Min Act: -0.1700
Data Index: 6851509 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.6148. Min Act: -0.1700
Data Index: 1309464 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.6148. Min Act: -0.1700
Data Index: 3011095 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5987. Min Act: -0.1700
Data Index: 591913 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5987. Min Act: -0.1700
Data Index: 1015110 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5987. Min Act: -0.1700
Data Index: 1974774 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5504. Min Act: -0.1700
Data Index: 6044762 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5665. Min Act: -0.1700
Data Index: 902818 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5987. Min Act: -0.1700
Data Index: 4460031 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5665. Min Act: -0.1700
Data Index: 8324155 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5826. Min Act: -0.1700
Data Index: 920233 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5504. Min Act: -0.1700
Data Index: 6210851 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5665. Min Act: -0.1700
Data Index: 3086261 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5987. Min Act: -0.1700
Data Index: 3765480 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5826. Min Act: -0.1700
Data Index: 3646633 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5504. Min Act: -0.1700
Data Index: 8509425 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7110. Min Range: -2.7110
Max Act: 2.5504. Min Act: -0.1700
Data Index: 5468384 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19