Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 763 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4120. Min Range: -8.4120
Max Act: 8.4120. Min Act: -0.1700
Data Index: 7867024 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4120. Min Range: -8.4120
Max Act: 8.0995. Min Act: -0.1700
Data Index: 328384 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4120. Min Range: -8.4120
Max Act: 8.0995. Min Act: -0.1700
Data Index: 2531811 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4120. Min Range: -8.4120
Max Act: 8.0370. Min Act: -0.1700
Data Index: 2801537 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4120. Min Range: -8.4120
Max Act: 8.0370. Min Act: -0.1700
Data Index: 7679997 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4120. Min Range: -8.4120
Max Act: 8.0370. Min Act: -0.1700
Data Index: 7144263 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.9745. Min Act: -0.1700
Data Index: 3622961 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.9120. Min Act: -0.1700
Data Index: 6719009 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.9120. Min Act: -0.1700
Data Index: 8521411 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.7870. Min Act: -0.1700
Data Index: 2401110 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.7557. Min Act: -0.1700
Data Index: 2447258 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.7245. Min Act: -0.1700
Data Index: 4834356 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.7245. Min Act: -0.1700
Data Index: 3626459 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.6620. Min Act: -0.1700
Data Index: 3011110 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.6307. Min Act: -0.1700
Data Index: 2367134 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.5995. Min Act: -0.1700
Data Index: 3103365 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.5995. Min Act: -0.1700
Data Index: 7089177 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.5682. Min Act: -0.1700
Data Index: 7885311 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.5057. Min Act: -0.1700
Data Index: 7753600 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4120. Min Range: -8.4120
Max Act: 7.5057. Min Act: -0.1700
Data Index: 7335934 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19