Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3971 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.6009. Min Act: -0.1700
Data Index: 7178303 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5697. Min Act: -0.1700
Data Index: 7093950 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5384. Min Act: -0.1700
Data Index: 5268909 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5384. Min Act: -0.1700
Data Index: 6459891 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5384. Min Act: -0.1700
Data Index: 1622223 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5384. Min Act: -0.1700
Data Index: 2816424 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5384. Min Act: -0.1700
Data Index: 4483921 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5072. Min Act: -0.1700
Data Index: 3867877 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5384. Min Act: -0.1700
Data Index: 776320 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5072. Min Act: -0.1700
Data Index: 7943436 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.5072. Min Act: -0.1700
Data Index: 5960195 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4759. Min Act: -0.1700
Data Index: 8699295 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4759. Min Act: -0.1700
Data Index: 8253546 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4447. Min Act: -0.1700
Data Index: 4722032 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4759. Min Act: -0.1700
Data Index: 7988080 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4447. Min Act: -0.1700
Data Index: 5707250 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4447. Min Act: -0.1700
Data Index: 2781610 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4447. Min Act: -0.1700
Data Index: 1080596 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4134. Min Act: -0.1700
Data Index: 6395654 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6009. Min Range: -5.6009
Max Act: 5.4447. Min Act: -0.1700
Data Index: 3921110 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19