Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 444 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3218. Min Range: -7.3218
Max Act: 7.0406. Min Act: -0.1700
Data Index: 4359103 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5718. Min Act: -0.1700
Data Index: 3532000 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3218. Min Range: -7.3218
Max Act: 7.3218. Min Act: -0.1700
Data Index: 8082844 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.8218. Min Act: -0.1700
Data Index: 3072620 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.7281. Min Act: -0.1700
Data Index: 2135695 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.6031. Min Act: -0.1700
Data Index: 6317438 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.6031. Min Act: -0.1700
Data Index: 4928251 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5406. Min Act: -0.1700
Data Index: 1406860 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.6968. Min Act: -0.1700
Data Index: 3647931 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.6343. Min Act: -0.1700
Data Index: 678889 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.1031. Min Act: -0.1700
Data Index: 4542538 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5093. Min Act: -0.1700
Data Index: 7768296 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.6031. Min Act: -0.1700
Data Index: 7034586 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5718. Min Act: -0.1700
Data Index: 7022364 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5718. Min Act: -0.1700
Data Index: 6876231 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5406. Min Act: -0.1700
Data Index: 4887207 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5093. Min Act: -0.1700
Data Index: 1814241 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5093. Min Act: -0.1700
Data Index: 2562414 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.5093. Min Act: -0.1698
Data Index: 1214710 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3218. Min Range: -7.3218
Max Act: 6.4781. Min Act: -0.1700
Data Index: 6653783 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19