Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.7074. Min Act: -0.1700
Data Index: 7793825 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.6762. Min Act: -0.1700
Data Index: 8801048 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.6137. Min Act: -0.1700
Data Index: 4925936 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.6137. Min Act: -0.1700
Data Index: 5752783 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5824. Min Act: -0.1700
Data Index: 8219457 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5824. Min Act: -0.1700
Data Index: 7396606 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5512. Min Act: -0.1700
Data Index: 898912 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5512. Min Act: -0.1700
Data Index: 7838955 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5512. Min Act: -0.1700
Data Index: 2871785 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5512. Min Act: -0.1700
Data Index: 4968695 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5512. Min Act: -0.1700
Data Index: 3293567 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5199. Min Act: -0.1700
Data Index: 7575993 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.4887. Min Act: -0.1700
Data Index: 2888816 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.4887. Min Act: -0.1700
Data Index: 4831886 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.5199. Min Act: -0.1700
Data Index: 898907 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.4887. Min Act: -0.1700
Data Index: 7729689 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.4887. Min Act: -0.1700
Data Index: 1452650 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.4887. Min Act: -0.1700
Data Index: 966532 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.4574. Min Act: -0.1700
Data Index: 1009656 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7074. Min Range: -5.7074
Max Act: 5.4887. Min Act: -0.1700
Data Index: 3037108 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19