Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3982. Min Range: -9.3982
Max Act: 9.3982. Min Act: -0.1700
Data Index: 3165153 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3982. Min Range: -9.3982
Max Act: 9.3357. Min Act: -0.1700
Data Index: 3165139 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3982. Min Range: -9.3982
Max Act: 9.0857. Min Act: -0.1700
Data Index: 966358 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3982. Min Range: -9.3982
Max Act: 9.0232. Min Act: -0.1700
Data Index: 4744958 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.9607. Min Act: -0.1700
Data Index: 1153927 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3982. Min Range: -9.3982
Max Act: 9.0232. Min Act: -0.1700
Data Index: 2926522 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.9607. Min Act: -0.1700
Data Index: 8198581 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.9607. Min Act: -0.1700
Data Index: 7785974 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.9607. Min Act: -0.1700
Data Index: 7785996 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8982. Min Act: -0.1700
Data Index: 7177048 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8982. Min Act: -0.1700
Data Index: 7177043 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8982. Min Act: -0.1700
Data Index: 3165140 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8357. Min Act: -0.1700
Data Index: 7785977 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.7732. Min Act: -0.1700
Data Index: 966357 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8357. Min Act: -0.1700
Data Index: 4744960 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8357. Min Act: -0.1700
Data Index: 3165149 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8357. Min Act: -0.1700
Data Index: 4744959 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8357. Min Act: -0.1700
Data Index: 7785973 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8357. Min Act: -0.1700
Data Index: 3165135 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3982. Min Range: -9.3982
Max Act: 8.8357. Min Act: -0.1700
Data Index: 3165136 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19