Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4976 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.3125. Min Act: -0.1700
Data Index: 4497358 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.0625. Min Act: -0.1700
Data Index: 8135763 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.0625. Min Act: -0.1700
Data Index: 5014 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.0625. Min Act: -0.1700
Data Index: 2011598 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.0000. Min Act: -0.1700
Data Index: 6888849 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.0000. Min Act: -0.1700
Data Index: 8341049 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.9375. Min Act: -0.1700
Data Index: 1100587 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.9375. Min Act: -0.1700
Data Index: 6462483 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.0000. Min Act: -0.1700
Data Index: 4025724 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.8750. Min Act: -0.1700
Data Index: 2851900 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.8750. Min Act: -0.1700
Data Index: 4912848 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.8125. Min Act: -0.1700
Data Index: 7244743 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6875. Min Act: -0.1700
Data Index: 983029 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7500. Min Act: -0.1700
Data Index: 4514384 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7500. Min Act: -0.1700
Data Index: 2176939 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.8125. Min Act: -0.1700
Data Index: 6051213 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7500. Min Act: -0.1700
Data Index: 2108796 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6875. Min Act: -0.1700
Data Index: 859720 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6875. Min Act: -0.1700
Data Index: 1638215 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6875. Min Act: -0.1700
Data Index: 6401763 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19