Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9074. Min Range: -7.9074
Max Act: 7.9074. Min Act: -0.1700
Data Index: 8054244 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9074. Min Range: -7.9074
Max Act: 7.5324. Min Act: -0.1700
Data Index: 2996419 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9074. Min Range: -7.9074
Max Act: 7.2199. Min Act: -0.1700
Data Index: 8164617 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9074. Min Range: -7.9074
Max Act: 7.1574. Min Act: -0.1700
Data Index: 8532020 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9074. Min Range: -7.9074
Max Act: 7.1262. Min Act: -0.1700
Data Index: 5776114 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9074. Min Range: -7.9074
Max Act: 7.0949. Min Act: -0.1700
Data Index: 2368845 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9074. Min Range: -7.9074
Max Act: 7.0324. Min Act: -0.1700
Data Index: 5647293 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9074. Min Range: -7.9074
Max Act: 7.0324. Min Act: -0.1700
Data Index: 3555583 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.9699. Min Act: -0.1700
Data Index: 3571834 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.8762. Min Act: -0.1700
Data Index: 7772892 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.9387. Min Act: -0.1700
Data Index: 924751 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.8449. Min Act: -0.1700
Data Index: 6010576 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.8762. Min Act: -0.1700
Data Index: 7689039 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.8449. Min Act: -0.1700
Data Index: 2195785 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.7824. Min Act: -0.1700
Data Index: 7689042 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.8137. Min Act: -0.1700
Data Index: 7818522 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.8449. Min Act: -0.1700
Data Index: 855919 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.7512. Min Act: -0.1700
Data Index: 2025293 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.7199. Min Act: -0.1700
Data Index: 5898102 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9074. Min Range: -7.9074
Max Act: 6.7512. Min Act: -0.1700
Data Index: 3839317 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19