Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3848 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.5186. Min Act: -0.1700
Data Index: 7289902 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.5186. Min Act: -0.1700
Data Index: 1815781 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.4561. Min Act: -0.1700
Data Index: 8000313 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.4249. Min Act: -0.1700
Data Index: 5589962 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.4249. Min Act: -0.1700
Data Index: 5589963 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.4249. Min Act: -0.1700
Data Index: 4102034 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.3624. Min Act: -0.1700
Data Index: 8730107 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.3936. Min Act: -0.1700
Data Index: 5217933 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.3936. Min Act: -0.1700
Data Index: 2175899 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.3624. Min Act: -0.1700
Data Index: 7835456 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.3311. Min Act: -0.1700
Data Index: 2118963 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.2999. Min Act: -0.1700
Data Index: 5652795 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.2999. Min Act: -0.1700
Data Index: 899930 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.3311. Min Act: -0.1700
Data Index: 3316831 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.2999. Min Act: -0.1700
Data Index: 4027522 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.2999. Min Act: -0.1700
Data Index: 2006956 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.2999. Min Act: -0.1700
Data Index: 5784890 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.2999. Min Act: -0.1700
Data Index: 6667066 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.2999. Min Act: -0.1700
Data Index: 6381539 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5186. Min Range: -5.5186
Max Act: 5.3311. Min Act: -0.1700
Data Index: 35182 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19