Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4976. Min Range: -6.4976
Max Act: 6.4976. Min Act: -0.1700
Data Index: 2126048 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4976. Min Range: -6.4976
Max Act: 6.2164. Min Act: -0.1700
Data Index: 4248493 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4976. Min Range: -6.4976
Max Act: 6.1851. Min Act: -0.1700
Data Index: 8163139 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.9664. Min Act: -0.1700
Data Index: 5567831 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.9039. Min Act: -0.1700
Data Index: 6534700 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.7789. Min Act: -0.1700
Data Index: 6600601 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.7476. Min Act: -0.1700
Data Index: 6148880 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.7476. Min Act: -0.1700
Data Index: 5881421 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.6851. Min Act: -0.1700
Data Index: 2939855 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.7164. Min Act: -0.1700
Data Index: 1573025 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.7164. Min Act: -0.1700
Data Index: 1275524 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.6851. Min Act: -0.1700
Data Index: 4006954 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.6851. Min Act: -0.1700
Data Index: 8602247 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.6226. Min Act: -0.1700
Data Index: 1660104 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.6539. Min Act: -0.1700
Data Index: 4104308 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.6539. Min Act: -0.1700
Data Index: 8552707 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.5914. Min Act: -0.1700
Data Index: 4349496 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.6226. Min Act: -0.1700
Data Index: 8568412 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.5914. Min Act: -0.1700
Data Index: 1627025 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4976. Min Range: -6.4976
Max Act: 5.5914. Min Act: -0.1700
Data Index: 1288640 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19