Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0045. Min Range: -6.0045
Max Act: 6.0045. Min Act: -0.1700
Data Index: 904257 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0045. Min Range: -6.0045
Max Act: 6.0045. Min Act: -0.1700
Data Index: 1101503 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.9420. Min Act: -0.1700
Data Index: 747552 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.9420. Min Act: -0.1700
Data Index: 5197898 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.9420. Min Act: -0.1700
Data Index: 5963782 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.9108. Min Act: -0.1700
Data Index: 2638910 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.9108. Min Act: -0.1700
Data Index: 3065846 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.9108. Min Act: -0.1700
Data Index: 2769405 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.9108. Min Act: -0.1700
Data Index: 39 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.8795. Min Act: -0.1700
Data Index: 5034486 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.8795. Min Act: -0.1700
Data Index: 4224547 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.8795. Min Act: -0.1700
Data Index: 5179020 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.8170. Min Act: -0.1700
Data Index: 5978148 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.8483. Min Act: -0.1700
Data Index: 4716844 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.7858. Min Act: -0.1700
Data Index: 8802694 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.8170. Min Act: -0.1700
Data Index: 2411690 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.7858. Min Act: -0.1700
Data Index: 7026007 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.7858. Min Act: -0.1700
Data Index: 5847659 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.7545. Min Act: -0.1700
Data Index: 6698811 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0045. Min Range: -6.0045
Max Act: 5.7233. Min Act: -0.1700
Data Index: 5114255 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19