Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4785 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0405. Min Range: -3.0405
Max Act: 3.0405. Min Act: -0.1700
Data Index: 4704206 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0405. Min Range: -3.0405
Max Act: 3.0247. Min Act: -0.1700
Data Index: 6420577 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.9773. Min Act: -0.1700
Data Index: 921859 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.9773. Min Act: -0.1700
Data Index: 818184 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.9615. Min Act: -0.1700
Data Index: 7896963 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.9299. Min Act: -0.1700
Data Index: 5601046 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.9140. Min Act: -0.1700
Data Index: 852274 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8982. Min Act: -0.1700
Data Index: 6907986 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8982. Min Act: -0.1700
Data Index: 4947772 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8982. Min Act: -0.1700
Data Index: 7212899 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8823. Min Act: -0.1700
Data Index: 142644 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8505. Min Act: -0.1700
Data Index: 8135661 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8505. Min Act: -0.1700
Data Index: 5082609 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8505. Min Act: -0.1700
Data Index: 1743824 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8505. Min Act: -0.1700
Data Index: 7895803 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8346. Min Act: -0.1700
Data Index: 6837521 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8346. Min Act: -0.1700
Data Index: 6860486 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.8187. Min Act: -0.1700
Data Index: 3240268 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.7709. Min Act: -0.1700
Data Index: 5709049 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0405. Min Range: -3.0405
Max Act: 2.7709. Min Act: -0.1700
Data Index: 5445595 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19