Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4883 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1837. Min Range: -9.1837
Max Act: 9.1837. Min Act: -0.1700
Data Index: 4454052 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1837. Min Range: -9.1837
Max Act: 9.1212. Min Act: -0.1700
Data Index: 3349106 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.9337. Min Act: -0.1700
Data Index: 2333422 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.6212. Min Act: -0.1700
Data Index: 1317548 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.5587. Min Act: -0.1700
Data Index: 7095949 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.5275. Min Act: -0.1700
Data Index: 7104814 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.5275. Min Act: -0.1700
Data Index: 852251 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.4962. Min Act: -0.1700
Data Index: 951186 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.4337. Min Act: -0.1700
Data Index: 5375608 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.4962. Min Act: -0.1700
Data Index: 7532358 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.4025. Min Act: -0.1700
Data Index: 5002343 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.4337. Min Act: -0.1700
Data Index: 6981787 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.4025. Min Act: -0.1700
Data Index: 4495700 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.3712. Min Act: -0.1700
Data Index: 6432572 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.3087. Min Act: -0.1700
Data Index: 8461804 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.3087. Min Act: -0.1700
Data Index: 1414488 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.3400. Min Act: -0.1700
Data Index: 5444706 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.2775. Min Act: -0.1700
Data Index: 3491190 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.2775. Min Act: -0.1700
Data Index: 8009785 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1837. Min Range: -9.1837
Max Act: 8.2462. Min Act: -0.1700
Data Index: 7855666 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19