Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3350. Min Range: -9.3350
Max Act: 9.3350. Min Act: -0.1700
Data Index: 1851108 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3350. Min Range: -9.3350
Max Act: 9.2100. Min Act: -0.1700
Data Index: 7136033 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3350. Min Range: -9.3350
Max Act: 9.1475. Min Act: -0.1700
Data Index: 3792931 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3350. Min Range: -9.3350
Max Act: 9.1475. Min Act: -0.1700
Data Index: 2784492 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3350. Min Range: -9.3350
Max Act: 9.0850. Min Act: -0.1700
Data Index: 142319 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3350. Min Range: -9.3350
Max Act: 9.0225. Min Act: -0.1700
Data Index: 982066 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.9600. Min Act: -0.1700
Data Index: 4015882 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.8975. Min Act: -0.1700
Data Index: 4463350 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.8350. Min Act: -0.1700
Data Index: 8261146 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.7725. Min Act: -0.1700
Data Index: 4291074 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.7725. Min Act: -0.1700
Data Index: 8417215 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.8350. Min Act: -0.1700
Data Index: 2557496 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.7725. Min Act: -0.1700
Data Index: 2946923 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.7100. Min Act: -0.1700
Data Index: 173890 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.6475. Min Act: -0.1700
Data Index: 4818390 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.7100. Min Act: -0.1700
Data Index: 1381328 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.6475. Min Act: -0.1700
Data Index: 7232915 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.5850. Min Act: -0.1700
Data Index: 1625092 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.5850. Min Act: -0.1700
Data Index: 2879926 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3350. Min Range: -9.3350
Max Act: 8.5850. Min Act: -0.1700
Data Index: 3790642 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19