Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.5847. Min Act: -0.1700
Data Index: 4443784 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.5847. Min Act: -0.1700
Data Index: 4042966 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.5222. Min Act: -0.1700
Data Index: 2226341 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.4597. Min Act: -0.1700
Data Index: 4188164 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.4597. Min Act: -0.1700
Data Index: 4666465 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.4597. Min Act: -0.1700
Data Index: 8373738 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.4597. Min Act: -0.1700
Data Index: 1714992 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.3972. Min Act: -0.1700
Data Index: 5209446 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.2097. Min Act: -0.1700
Data Index: 741392 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.2722. Min Act: -0.1700
Data Index: 520479 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.2097. Min Act: -0.1700
Data Index: 4685545 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.2097. Min Act: -0.1700
Data Index: 276937 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.2097. Min Act: -0.1700
Data Index: 3147700 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.1785. Min Act: -0.1700
Data Index: 1888763 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.2097. Min Act: -0.1700
Data Index: 4813773 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.0847. Min Act: -0.1700
Data Index: 5306000 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.0222. Min Act: -0.1700
Data Index: 5605760 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5847. Min Range: -8.5847
Max Act: 7.9910. Min Act: -0.1700
Data Index: 7807239 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.0222. Min Act: -0.1700
Data Index: 4321190 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5847. Min Range: -8.5847
Max Act: 8.0222. Min Act: -0.1700
Data Index: 5018774 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19