Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 472 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2087. Min Range: -7.2087
Max Act: 7.2087. Min Act: -0.1700
Data Index: 4592086 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.9274. Min Act: -0.1700
Data Index: 1333828 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8649. Min Act: -0.1700
Data Index: 1410776 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8649. Min Act: -0.1700
Data Index: 7681289 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8024. Min Act: -0.1700
Data Index: 3015894 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8024. Min Act: -0.1700
Data Index: 7301690 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8024. Min Act: -0.1700
Data Index: 4151530 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.7399. Min Act: -0.1700
Data Index: 7143868 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6774. Min Act: -0.1700
Data Index: 4512417 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6774. Min Act: -0.1700
Data Index: 569910 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6774. Min Act: -0.1700
Data Index: 3292226 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6462. Min Act: -0.1700
Data Index: 2601086 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6462. Min Act: -0.1700
Data Index: 3200329 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6462. Min Act: -0.1700
Data Index: 1527298 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6149. Min Act: -0.1700
Data Index: 6260241 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6149. Min Act: -0.1700
Data Index: 5989786 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6149. Min Act: -0.1700
Data Index: 3853165 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6462. Min Act: -0.1700
Data Index: 4188633 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6149. Min Act: -0.1700
Data Index: 77 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.6149. Min Act: -0.1700
Data Index: 6678944 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19