Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1651 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1271. Min Range: -6.1271
Max Act: 6.1271. Min Act: -0.1700
Data Index: 3122976 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8458. Min Act: -0.1700
Data Index: 2197528 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6896. Min Act: -0.1700
Data Index: 6560801 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5646. Min Act: -0.1700
Data Index: 8771086 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5958. Min Act: -0.1700
Data Index: 3751090 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5333. Min Act: -0.1700
Data Index: 3907645 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5021. Min Act: -0.1700
Data Index: 6032039 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5021. Min Act: -0.1700
Data Index: 7027432 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.4396. Min Act: -0.1700
Data Index: 5416394 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.4396. Min Act: -0.1700
Data Index: 1658247 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.4396. Min Act: -0.1700
Data Index: 8513981 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.4083. Min Act: -0.1700
Data Index: 5239136 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.4083. Min Act: -0.1700
Data Index: 2377657 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.4396. Min Act: -0.1700
Data Index: 7943926 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.3771. Min Act: -0.1700
Data Index: 75924 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.3771. Min Act: -0.1700
Data Index: 5309412 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.3771. Min Act: -0.1700
Data Index: 6064952 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.3458. Min Act: -0.1700
Data Index: 3791004 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.3458. Min Act: -0.1700
Data Index: 5701841 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.3458. Min Act: -0.1700
Data Index: 2077448 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19