Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1147 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3152. Min Range: -6.3152
Max Act: 6.3152. Min Act: -0.1700
Data Index: 144740 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3152. Min Range: -6.3152
Max Act: 6.2527. Min Act: -0.1700
Data Index: 2793767 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3152. Min Range: -6.3152
Max Act: 6.2527. Min Act: -0.1700
Data Index: 413815 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3152. Min Range: -6.3152
Max Act: 6.1902. Min Act: -0.1700
Data Index: 5081200 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3152. Min Range: -6.3152
Max Act: 6.0652. Min Act: -0.1700
Data Index: 7645354 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3152. Min Range: -6.3152
Max Act: 6.0027. Min Act: -0.1700
Data Index: 5065282 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3152. Min Range: -6.3152
Max Act: 6.0027. Min Act: -0.1700
Data Index: 7128533 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.9402. Min Act: -0.1700
Data Index: 3034255 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.9402. Min Act: -0.1700
Data Index: 3568521 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.9402. Min Act: -0.1700
Data Index: 4824955 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.9089. Min Act: -0.1700
Data Index: 2585721 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8777. Min Act: -0.1700
Data Index: 1065614 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8777. Min Act: -0.1700
Data Index: 3430614 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8464. Min Act: -0.1700
Data Index: 468237 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8464. Min Act: -0.1700
Data Index: 8246633 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8464. Min Act: -0.1700
Data Index: 1353103 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8464. Min Act: -0.1700
Data Index: 1501489 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8464. Min Act: -0.1700
Data Index: 5142823 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8464. Min Act: -0.1700
Data Index: 4832390 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3152. Min Range: -6.3152
Max Act: 5.8152. Min Act: -0.1700
Data Index: 6167042 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19