Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1385 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.8587. Min Act: -0.1700
Data Index: 6153116 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.7951. Min Act: -0.1700
Data Index: 8724513 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6993. Min Act: -0.1700
Data Index: 6225978 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6512. Min Act: -0.1700
Data Index: 1939302 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6673. Min Act: -0.1700
Data Index: 1235497 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6512. Min Act: -0.1700
Data Index: 422136 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6512. Min Act: -0.1700
Data Index: 4938264 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6512. Min Act: -0.1700
Data Index: 5331002 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6352. Min Act: -0.1700
Data Index: 4616917 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6191. Min Act: -0.1700
Data Index: 3641842 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6191. Min Act: -0.1700
Data Index: 3026197 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6030. Min Act: -0.1700
Data Index: 3897190 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6030. Min Act: -0.1700
Data Index: 7591945 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.6030. Min Act: -0.1700
Data Index: 6761257 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.5869. Min Act: -0.1700
Data Index: 2190441 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.5869. Min Act: -0.1700
Data Index: 7501206 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.5708. Min Act: -0.1700
Data Index: 1654878 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.5869. Min Act: -0.1700
Data Index: 2198924 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.5708. Min Act: -0.1700
Data Index: 4123189 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8587. Min Range: -2.8587
Max Act: 2.5708. Min Act: -0.1700
Data Index: 4722726 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19