Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4035 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1501. Min Range: -9.1501
Max Act: 9.1501. Min Act: -0.1700
Data Index: 6355190 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1501. Min Range: -9.1501
Max Act: 9.0876. Min Act: -0.1700
Data Index: 7169888 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.9626. Min Act: -0.1700
Data Index: 4201694 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.9626. Min Act: -0.1700
Data Index: 4355207 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.9001. Min Act: -0.1700
Data Index: 5990745 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.7126. Min Act: -0.1700
Data Index: 4722985 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.7751. Min Act: -0.1700
Data Index: 6355191 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.7126. Min Act: -0.1700
Data Index: 363331 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.7126. Min Act: -0.1700
Data Index: 2339474 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.6501. Min Act: -0.1700
Data Index: 7566226 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.5876. Min Act: -0.1700
Data Index: 7031988 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.6501. Min Act: -0.1700
Data Index: 4355208 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.6501. Min Act: -0.1700
Data Index: 3876855 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.5876. Min Act: -0.1700
Data Index: 8543714 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.5876. Min Act: -0.1700
Data Index: 4722992 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.5876. Min Act: -0.1700
Data Index: 7348861 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.5251. Min Act: -0.1700
Data Index: 2327382 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.5251. Min Act: -0.1700
Data Index: 3968023 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.5251. Min Act: -0.1700
Data Index: 4722990 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1501. Min Range: -9.1501
Max Act: 8.5251. Min Act: -0.1700
Data Index: 4829958 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19