Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0051. Min Range: -6.0051
Max Act: 6.0051. Min Act: -0.1700
Data Index: 5056449 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.7863. Min Act: -0.1700
Data Index: 6370933 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.7238. Min Act: -0.1700
Data Index: 1367438 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.7238. Min Act: -0.1700
Data Index: 8030689 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.6613. Min Act: -0.1700
Data Index: 1778775 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.6926. Min Act: -0.1700
Data Index: 3471818 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.6926. Min Act: -0.1700
Data Index: 7022021 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.6613. Min Act: -0.1700
Data Index: 523747 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.6613. Min Act: -0.1700
Data Index: 1902543 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.6301. Min Act: -0.1700
Data Index: 1185424 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.5988. Min Act: -0.1700
Data Index: 8830611 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.6301. Min Act: -0.1700
Data Index: 4489121 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.6613. Min Act: -0.1700
Data Index: 4707965 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.5988. Min Act: -0.1700
Data Index: 6613013 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.5988. Min Act: -0.1700
Data Index: 5989316 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.5676. Min Act: -0.1700
Data Index: 7426116 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.5988. Min Act: -0.1700
Data Index: 4372301 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.5988. Min Act: -0.1700
Data Index: 4478625 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.5676. Min Act: -0.1700
Data Index: 1778870 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0051. Min Range: -6.0051
Max Act: 5.5676. Min Act: -0.1700
Data Index: 4395340 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19