Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6367 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0107. Min Range: -5.0107
Max Act: 5.0107. Min Act: -0.1700
Data Index: 8546604 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.9170. Min Act: -0.1700
Data Index: 4673764 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.8857. Min Act: -0.1700
Data Index: 7982116 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.8232. Min Act: -0.1700
Data Index: 4153577 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.7607. Min Act: -0.1700
Data Index: 478651 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.7607. Min Act: -0.1700
Data Index: 1529921 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.7295. Min Act: -0.1700
Data Index: 2085703 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6982. Min Act: -0.1700
Data Index: 5525053 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6982. Min Act: -0.1700
Data Index: 725607 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6982. Min Act: -0.1700
Data Index: 3051243 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6670. Min Act: -0.1700
Data Index: 532417 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6357. Min Act: -0.1700
Data Index: 5370925 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6670. Min Act: -0.1700
Data Index: 5160556 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6670. Min Act: -0.1700
Data Index: 5012417 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6357. Min Act: -0.1700
Data Index: 1784160 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6045. Min Act: -0.1700
Data Index: 1630453 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.6045. Min Act: -0.1700
Data Index: 7083315 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.5732. Min Act: -0.1700
Data Index: 1992030 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.5732. Min Act: -0.1700
Data Index: 1591975 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0107. Min Range: -5.0107
Max Act: 4.5732. Min Act: -0.1700
Data Index: 5500995 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19