Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3795 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.9363. Min Act: -0.1700
Data Index: 1370733 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.9051. Min Act: -0.1700
Data Index: 572824 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.8738. Min Act: -0.1700
Data Index: 1699021 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.8113. Min Act: -0.1700
Data Index: 6258653 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.6863. Min Act: -0.1700
Data Index: 2390916 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.6551. Min Act: -0.1700
Data Index: 7517640 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.6238. Min Act: -0.1700
Data Index: 5422976 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6872250 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6356458 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.6238. Min Act: -0.1700
Data Index: 5505932 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5926. Min Act: -0.1700
Data Index: 3153443 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5926. Min Act: -0.1700
Data Index: 5920442 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5926. Min Act: -0.1698
Data Index: 8182222 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5613. Min Act: -0.1700
Data Index: 2289205 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5613. Min Act: -0.1700
Data Index: 4567793 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5613. Min Act: -0.1700
Data Index: 6677369 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5613. Min Act: -0.1700
Data Index: 1643727 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5613. Min Act: -0.1700
Data Index: 572826 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5613. Min Act: -0.1700
Data Index: 7370185 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9363. Min Range: -5.9363
Max Act: 5.5613. Min Act: -0.1700
Data Index: 4614100 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19