Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4941 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1015. Min Range: -8.1015
Max Act: 8.1015. Min Act: -0.1700
Data Index: 169680 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.7890. Min Act: -0.1700
Data Index: 5826264 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.5702. Min Act: -0.1700
Data Index: 3105167 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.4452. Min Act: -0.1700
Data Index: 7165716 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.4140. Min Act: -0.1700
Data Index: 3521706 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.3202. Min Act: -0.1700
Data Index: 6684182 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.1952. Min Act: -0.1700
Data Index: 2476373 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.1952. Min Act: -0.1700
Data Index: 1196835 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.1952. Min Act: -0.1700
Data Index: 1440069 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.1327. Min Act: -0.1700
Data Index: 876764 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.1640. Min Act: -0.1700
Data Index: 2493330 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.1327. Min Act: -0.1700
Data Index: 3556641 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.1015. Min Act: -0.1700
Data Index: 4535015 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.1015. Min Act: -0.1700
Data Index: 7958331 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.0702. Min Act: -0.1700
Data Index: 8755585 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1015. Min Range: -8.1015
Max Act: 7.0077. Min Act: -0.1700
Data Index: 3752521 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1015. Min Range: -8.1015
Max Act: 6.9765. Min Act: -0.1700
Data Index: 1086442 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1015. Min Range: -8.1015
Max Act: 6.9765. Min Act: -0.1700
Data Index: 2924586 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1015. Min Range: -8.1015
Max Act: 6.9765. Min Act: -0.1700
Data Index: 2992739 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1015. Min Range: -8.1015
Max Act: 6.9452. Min Act: -0.1700
Data Index: 6087702 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19