Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 963 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2750. Min Range: -7.2750
Max Act: 7.2750. Min Act: -0.1700
Data Index: 4886285 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2750. Min Range: -7.2750
Max Act: 7.2750. Min Act: -0.1700
Data Index: 8743117 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2750. Min Range: -7.2750
Max Act: 7.0250. Min Act: -0.1700
Data Index: 379676 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2750. Min Range: -7.2750
Max Act: 7.0250. Min Act: -0.1700
Data Index: 7188632 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.9938. Min Act: -0.1700
Data Index: 7319979 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.9625. Min Act: -0.1700
Data Index: 8335693 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.9000. Min Act: -0.1700
Data Index: 4193730 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.8375. Min Act: -0.1700
Data Index: 4105737 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.8063. Min Act: -0.1700
Data Index: 1594009 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.8063. Min Act: -0.1700
Data Index: 8763669 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.7125. Min Act: -0.1700
Data Index: 6678319 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.7125. Min Act: -0.1700
Data Index: 3733853 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.7125. Min Act: -0.1700
Data Index: 4217001 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.7125. Min Act: -0.1700
Data Index: 4950602 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.6813. Min Act: -0.1700
Data Index: 6207132 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.6813. Min Act: -0.1700
Data Index: 679097 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.6813. Min Act: -0.1700
Data Index: 8423325 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.6500. Min Act: -0.1700
Data Index: 5747533 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.6500. Min Act: -0.1700
Data Index: 8482694 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2750. Min Range: -7.2750
Max Act: 6.6500. Min Act: -0.1700
Data Index: 5955025 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19