Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2215 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1865. Min Range: -9.1865
Max Act: 9.1865. Min Act: -0.1700
Data Index: 8556115 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1865. Min Range: -9.1865
Max Act: 8.2490. Min Act: -0.1700
Data Index: 7674889 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1865. Min Range: -9.1865
Max Act: 8.1240. Min Act: -0.1700
Data Index: 6839722 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1865. Min Range: -9.1865
Max Act: 8.1240. Min Act: -0.1700
Data Index: 1220779 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1865. Min Range: -9.1865
Max Act: 8.0615. Min Act: -0.1700
Data Index: 6844842 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1865. Min Range: -9.1865
Max Act: 8.0615. Min Act: -0.1700
Data Index: 3961458 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1865. Min Range: -9.1865
Max Act: 8.0615. Min Act: -0.1700
Data Index: 7020509 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.9990. Min Act: -0.1700
Data Index: 2940313 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.9990. Min Act: -0.1700
Data Index: 3221431 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.9990. Min Act: -0.1700
Data Index: 6441127 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.9990. Min Act: -0.1700
Data Index: 3247102 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.9990. Min Act: -0.1700
Data Index: 7028713 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.9365. Min Act: -0.1700
Data Index: 3960894 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.9365. Min Act: -0.1700
Data Index: 2086616 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.9365. Min Act: -0.1700
Data Index: 8392925 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.8740. Min Act: -0.1700
Data Index: 6935035 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.8115. Min Act: -0.1700
Data Index: 2840274 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.7490. Min Act: -0.1700
Data Index: 3396122 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.7802. Min Act: -0.1700
Data Index: 1543613 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1865. Min Range: -9.1865
Max Act: 7.7490. Min Act: -0.1700
Data Index: 1083340 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19