Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1156 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.9885. Min Act: -0.1700
Data Index: 8612601 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.6760. Min Act: -0.1700
Data Index: 2030052 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.6135. Min Act: -0.1700
Data Index: 3971555 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.6135. Min Act: -0.1700
Data Index: 2962046 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.5510. Min Act: -0.1700
Data Index: 1741225 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.5510. Min Act: -0.1700
Data Index: 7963068 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4885. Min Act: -0.1700
Data Index: 6514068 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4885. Min Act: -0.1700
Data Index: 4116306 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4885. Min Act: -0.1700
Data Index: 7677581 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4573. Min Act: -0.1700
Data Index: 1604128 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4260. Min Act: -0.1700
Data Index: 8518117 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4573. Min Act: -0.1700
Data Index: 4272272 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4573. Min Act: -0.1700
Data Index: 7352051 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.3948. Min Act: -0.1700
Data Index: 1836508 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.3948. Min Act: -0.1700
Data Index: 4509657 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.3635. Min Act: -0.1700
Data Index: 1356754 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.3635. Min Act: -0.1700
Data Index: 4588185 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.3323. Min Act: -0.1700
Data Index: 7417843 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.3010. Min Act: -0.1700
Data Index: 4327733 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.3323. Min Act: -0.1700
Data Index: 2993598 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19