Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5966. Min Range: -9.5966
Max Act: 9.5966. Min Act: -0.1700
Data Index: 7714764 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5966. Min Range: -9.5966
Max Act: 9.0966. Min Act: -0.1700
Data Index: 7398753 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5966. Min Range: -9.5966
Max Act: 9.0341. Min Act: -0.1700
Data Index: 4052425 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5966. Min Range: -9.5966
Max Act: 6.9403. Min Act: -0.1700
Data Index: 827665 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5966. Min Range: -9.5966
Max Act: 8.5966. Min Act: -0.1700
Data Index: 3805593 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5966. Min Range: -9.5966
Max Act: 8.4716. Min Act: -0.1700
Data Index: 7398761 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5966. Min Range: -9.5966
Max Act: 8.2216. Min Act: -0.1698
Data Index: 1182500 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5966. Min Range: -9.5966
Max Act: 8.1591. Min Act: -0.1700
Data Index: 3060091 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5966. Min Range: -9.5966
Max Act: 8.2841. Min Act: -0.1700
Data Index: 5583480 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5966. Min Range: -9.5966
Max Act: 8.1591. Min Act: -0.1700
Data Index: 8145815 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5966. Min Range: -9.5966
Max Act: 8.0341. Min Act: -0.1700
Data Index: 2984329 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5966. Min Range: -9.5966
Max Act: 7.9716. Min Act: -0.1700
Data Index: 5299693 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5966. Min Range: -9.5966
Max Act: 8.0341. Min Act: -0.1700
Data Index: 4315375 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5966. Min Range: -9.5966
Max Act: 7.5966. Min Act: -0.1700
Data Index: 5853594 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5966. Min Range: -9.5966
Max Act: 7.9091. Min Act: -0.1700
Data Index: 6256071 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5966. Min Range: -9.5966
Max Act: 7.7841. Min Act: -0.1700
Data Index: 2222200 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5966. Min Range: -9.5966
Max Act: 7.9091. Min Act: -0.1700
Data Index: 7774977 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5966. Min Range: -9.5966
Max Act: 7.9091. Min Act: -0.1700
Data Index: 7678712 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5966. Min Range: -9.5966
Max Act: 7.3466. Min Act: -0.1700
Data Index: 7241936 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5966. Min Range: -9.5966
Max Act: 7.6591. Min Act: -0.1700
Data Index: 2100547 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19