Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3287 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.1106. Min Range: -17.1106
Max Act: 16.9856. Min Act: -0.1700
Data Index: 8596584 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.1106. Min Range: -17.1106
Max Act: 17.1106. Min Act: -0.1700
Data Index: 2729970 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.1106. Min Range: -17.1106
Max Act: 16.1731. Min Act: -0.1700
Data Index: 1682033 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.1106. Min Range: -17.1106
Max Act: 16.0481. Min Act: -0.1700
Data Index: 739036 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.7981. Min Act: -0.1700
Data Index: 2588376 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.7356. Min Act: -0.1700
Data Index: 3691137 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.6106. Min Act: -0.1700
Data Index: 6467248 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.5481. Min Act: -0.1700
Data Index: 464093 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.5481. Min Act: -0.1700
Data Index: 7390063 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.5481. Min Act: -0.1700
Data Index: 6883895 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.4231. Min Act: -0.1700
Data Index: 8074037 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.4856. Min Act: -0.1700
Data Index: 1317833 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.4856. Min Act: -0.1700
Data Index: 8352755 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.4231. Min Act: -0.1700
Data Index: 2607916 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.4231. Min Act: -0.1700
Data Index: 3513897 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.4231. Min Act: -0.1700
Data Index: 904217 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.3606. Min Act: -0.1700
Data Index: 5807110 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.3606. Min Act: -0.1700
Data Index: 5492968 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.3606. Min Act: -0.1700
Data Index: 6542944 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.1106. Min Range: -17.1106
Max Act: 15.2981. Min Act: -0.1700
Data Index: 1851606 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19