Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5567 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.8777. Min Act: -0.1700
Data Index: 6150471 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.8465. Min Act: -0.1700
Data Index: 6150461 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.5340. Min Act: -0.1700
Data Index: 920214 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.4402. Min Act: -0.1700
Data Index: 242956 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.4090. Min Act: -0.1700
Data Index: 6561620 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.3777. Min Act: -0.1700
Data Index: 6363684 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.3465. Min Act: -0.1700
Data Index: 764157 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.2840. Min Act: -0.1700
Data Index: 2937366 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.2215. Min Act: -0.1700
Data Index: 4584610 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.1902. Min Act: -0.1700
Data Index: 5004693 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.1590. Min Act: -0.1700
Data Index: 5660634 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0965. Min Act: -0.1700
Data Index: 1550017 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 3415099 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0965. Min Act: -0.1700
Data Index: 5059245 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0340. Min Act: -0.1700
Data Index: 4930756 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 2456498 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 3564435 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0027. Min Act: -0.1700
Data Index: 8390943 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0340. Min Act: -0.1700
Data Index: 8338909 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8777. Min Range: -7.8777
Max Act: 7.0340. Min Act: -0.1700
Data Index: 859107 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19