Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5343 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1294. Min Range: -8.1294
Max Act: 8.1294. Min Act: -0.1700
Data Index: 5419222 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1294. Min Range: -8.1294
Max Act: 8.0669. Min Act: -0.1700
Data Index: 2083374 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.9419. Min Act: -0.1700
Data Index: 246920 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.9419. Min Act: -0.1700
Data Index: 7403030 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.9419. Min Act: -0.1700
Data Index: 4712830 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.9419. Min Act: -0.1700
Data Index: 4568221 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8169. Min Act: -0.1700
Data Index: 915218 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8794. Min Act: -0.1700
Data Index: 3162866 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8169. Min Act: -0.1700
Data Index: 2211310 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8169. Min Act: -0.1700
Data Index: 185363 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8169. Min Act: -0.1700
Data Index: 1689210 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8169. Min Act: -0.1700
Data Index: 1272491 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8169. Min Act: -0.1700
Data Index: 864331 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8169. Min Act: -0.1700
Data Index: 3162863 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.8169. Min Act: -0.1700
Data Index: 1059298 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.7544. Min Act: -0.1700
Data Index: 6217448 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.7544. Min Act: -0.1700
Data Index: 5320835 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.7544. Min Act: -0.1700
Data Index: 1971036 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.7544. Min Act: -0.1700
Data Index: 1218611 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.7544. Min Act: -0.1700
Data Index: 6009105 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19