Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.4194. Min Act: -0.1700
Data Index: 561634 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.3569. Min Act: -0.1700
Data Index: 4219216 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.3257. Min Act: -0.1700
Data Index: 577172 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.2007. Min Act: -0.1700
Data Index: 6381512 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.0757. Min Act: -0.1700
Data Index: 4431086 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.0132. Min Act: -0.1700
Data Index: 4879241 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.0444. Min Act: -0.1700
Data Index: 3203310 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.0132. Min Act: -0.1700
Data Index: 7568910 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.0132. Min Act: -0.1700
Data Index: 6795339 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4194. Min Range: -6.4194
Max Act: 6.0132. Min Act: -0.1700
Data Index: 3196516 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9819. Min Act: -0.1700
Data Index: 3390764 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9819. Min Act: -0.1700
Data Index: 6195052 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9819. Min Act: -0.1700
Data Index: 7745112 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9507. Min Act: -0.1700
Data Index: 8394493 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9819. Min Act: -0.1700
Data Index: 203122 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9507. Min Act: -0.1700
Data Index: 2556357 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9194. Min Act: -0.1700
Data Index: 9151 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.8882. Min Act: -0.1700
Data Index: 5893757 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9194. Min Act: -0.1700
Data Index: 4702165 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4194. Min Range: -6.4194
Max Act: 5.9194. Min Act: -0.1700
Data Index: 5620434 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19