Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.9594. Min Act: -0.1700
Data Index: 6381752 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.8656. Min Act: -0.1700
Data Index: 4786274 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.7406. Min Act: -0.1700
Data Index: 2314284 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.7406. Min Act: -0.1700
Data Index: 454166 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.7406. Min Act: -0.1700
Data Index: 2314272 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.7406. Min Act: -0.1700
Data Index: 5053832 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.7406. Min Act: -0.1700
Data Index: 5444711 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.7094. Min Act: -0.1700
Data Index: 2314276 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6781. Min Act: -0.1700
Data Index: 8354697 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.7094. Min Act: -0.1700
Data Index: 4564678 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6781. Min Act: -0.1700
Data Index: 1915455 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6781. Min Act: -0.1700
Data Index: 177970 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6469. Min Act: -0.1700
Data Index: 459547 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6469. Min Act: -0.1700
Data Index: 3127664 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6469. Min Act: -0.1700
Data Index: 5444712 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6469. Min Act: -0.1700
Data Index: 2000235 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6469. Min Act: -0.1700
Data Index: 118322 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6469. Min Act: -0.1700
Data Index: 3748265 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6469. Min Act: -0.1700
Data Index: 3614002 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9594. Min Range: -4.9594
Max Act: 4.6469. Min Act: -0.1700
Data Index: 1439866 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19