Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.9267. Min Act: -0.1690
Data Index: 3640290 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8926. Min Act: -0.1700
Data Index: 7345421 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.9097. Min Act: -0.1698
Data Index: 2941713 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8756. Min Act: -0.1670
Data Index: 7389146 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8585. Min Act: -0.1695
Data Index: 2470153 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8585. Min Act: -0.1662
Data Index: 5692612 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1700
Data Index: 7345422 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1700
Data Index: 5044183 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1700
Data Index: 2246138 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1699
Data Index: 4936222 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1628
Data Index: 8319409 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1700
Data Index: 7197115 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1699
Data Index: 2537473 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1698
Data Index: 1708700 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1700
Data Index: 7509572 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1700
Data Index: 6210600 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1700
Data Index: 3676663 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8413. Min Act: -0.1700
Data Index: 5448762 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8070. Min Act: -0.1700
Data Index: 2843847 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9267. Min Range: -1.9267
Max Act: 1.8242. Min Act: -0.1698
Data Index: 1109118 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19