Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0911. Min Range: -8.0911
Max Act: 8.0911. Min Act: -0.1700
Data Index: 764111 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0911. Min Range: -8.0911
Max Act: 8.0286. Min Act: -0.1700
Data Index: 6448475 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0911. Min Range: -8.0911
Max Act: 8.0286. Min Act: -0.1700
Data Index: 3894183 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.9661. Min Act: -0.1700
Data Index: 7664639 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.9036. Min Act: -0.1700
Data Index: 7405950 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.9036. Min Act: -0.1700
Data Index: 6858911 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.8411. Min Act: -0.1700
Data Index: 2795852 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.8411. Min Act: -0.1700
Data Index: 4197263 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.8411. Min Act: -0.1700
Data Index: 1707595 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.7786. Min Act: -0.1700
Data Index: 4074039 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.7161. Min Act: -0.1700
Data Index: 4686748 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.7161. Min Act: -0.1700
Data Index: 2034046 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.6536. Min Act: -0.1700
Data Index: 4362930 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.6536. Min Act: -0.1700
Data Index: 2768758 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.6536. Min Act: -0.1700
Data Index: 6253504 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.6536. Min Act: -0.1700
Data Index: 5408438 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.5911. Min Act: -0.1700
Data Index: 4512694 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.5911. Min Act: -0.1700
Data Index: 3583767 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.5911. Min Act: -0.1700
Data Index: 4301701 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0911. Min Range: -8.0911
Max Act: 7.5911. Min Act: -0.1700
Data Index: 1978227 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19