Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.7100. Min Act: -0.1700
Data Index: 4106601 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.6475. Min Act: -0.1700
Data Index: 2620080 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.4600. Min Act: -0.1700
Data Index: 1630454 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.3975. Min Act: -0.1700
Data Index: 6831178 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.2725. Min Act: -0.1700
Data Index: 3545583 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.2100. Min Act: -0.1700
Data Index: 7999998 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.1475. Min Act: -0.1700
Data Index: 6198761 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.0850. Min Act: -0.1700
Data Index: 322991 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.0850. Min Act: -0.1700
Data Index: 8237194 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.0850. Min Act: -0.1700
Data Index: 918624 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7100. Min Range: -8.7100
Max Act: 7.9600. Min Act: -0.1700
Data Index: 2760140 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.0225. Min Act: -0.1700
Data Index: 3764589 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.0225. Min Act: -0.1700
Data Index: 6938345 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.0225. Min Act: -0.1700
Data Index: 959921 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7100. Min Range: -8.7100
Max Act: 8.0225. Min Act: -0.1700
Data Index: 711433 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7100. Min Range: -8.7100
Max Act: 7.9600. Min Act: -0.1700
Data Index: 3737799 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7100. Min Range: -8.7100
Max Act: 7.9600. Min Act: -0.1700
Data Index: 2555575 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7100. Min Range: -8.7100
Max Act: 7.8975. Min Act: -0.1700
Data Index: 460879 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7100. Min Range: -8.7100
Max Act: 7.8975. Min Act: -0.1700
Data Index: 7342306 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7100. Min Range: -8.7100
Max Act: 7.8975. Min Act: -0.1700
Data Index: 3520619 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19