Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.5032. Min Act: -0.1700
Data Index: 5905368 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.3782. Min Act: -0.1700
Data Index: 5338547 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.3157. Min Act: -0.1700
Data Index: 279316 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.3157. Min Act: -0.1700
Data Index: 2909177 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.2532. Min Act: -0.1700
Data Index: 6722962 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.2532. Min Act: -0.1700
Data Index: 7177384 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.1907. Min Act: -0.1700
Data Index: 6402779 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.1907. Min Act: -0.1700
Data Index: 1231953 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.1282. Min Act: -0.1700
Data Index: 5693034 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.1282. Min Act: -0.1700
Data Index: 2179988 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.1907. Min Act: -0.1700
Data Index: 2166598 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.1282. Min Act: -0.1700
Data Index: 8719525 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.0032. Min Act: -0.1700
Data Index: 745368 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.0657. Min Act: -0.1700
Data Index: 7267662 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.0657. Min Act: -0.1700
Data Index: 6518926 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.0657. Min Act: -0.1700
Data Index: 2586671 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.0032. Min Act: -0.1700
Data Index: 5905367 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.0032. Min Act: -0.1700
Data Index: 3024997 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.0657. Min Act: -0.1700
Data Index: 3095476 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5032. Min Range: -9.5032
Max Act: 9.0032. Min Act: -0.1700
Data Index: 8207163 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19