Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5582 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1519. Min Range: -6.1519
Max Act: 6.1519. Min Act: -0.1700
Data Index: 3277716 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1519. Min Range: -6.1519
Max Act: 6.0894. Min Act: -0.1700
Data Index: 4590878 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1519. Min Range: -6.1519
Max Act: 6.0894. Min Act: -0.1700
Data Index: 6603960 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1519. Min Range: -6.1519
Max Act: 6.0581. Min Act: -0.1700
Data Index: 4716260 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.9956. Min Act: -0.1700
Data Index: 6376119 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.9956. Min Act: -0.1700
Data Index: 3826941 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.9644. Min Act: -0.1700
Data Index: 3188189 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.9644. Min Act: -0.1700
Data Index: 8554203 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.9644. Min Act: -0.1700
Data Index: 1933854 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.9331. Min Act: -0.1700
Data Index: 2818951 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.9331. Min Act: -0.1700
Data Index: 544624 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.9331. Min Act: -0.1700
Data Index: 8550403 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.8706. Min Act: -0.1700
Data Index: 5642405 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.8706. Min Act: -0.1700
Data Index: 260081 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.8706. Min Act: -0.1700
Data Index: 4321512 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.8706. Min Act: -0.1700
Data Index: 6928400 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.8394. Min Act: -0.1700
Data Index: 3995780 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.8081. Min Act: -0.1700
Data Index: 722562 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.8081. Min Act: -0.1700
Data Index: 1237257 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1519. Min Range: -6.1519
Max Act: 5.7769. Min Act: -0.1700
Data Index: 6062404 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19