Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2108 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.7895. Min Act: -0.1700
Data Index: 3788433 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.6645. Min Act: -0.1700
Data Index: 67612 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.5082. Min Act: -0.1700
Data Index: 4027271 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.2895. Min Act: -0.1700
Data Index: 1935933 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.1020. Min Act: -0.1700
Data Index: 5202990 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.1020. Min Act: -0.1700
Data Index: 7624890 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.1332. Min Act: -0.1700
Data Index: 5569228 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.1020. Min Act: -0.1700
Data Index: 1893913 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.1020. Min Act: -0.1700
Data Index: 3341646 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.0395. Min Act: -0.1700
Data Index: 1056524 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.0395. Min Act: -0.1700
Data Index: 1149103 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.0395. Min Act: -0.1700
Data Index: 135666 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.0082. Min Act: -0.1700
Data Index: 4389894 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7895. Min Range: -6.7895
Max Act: 6.0082. Min Act: -0.1700
Data Index: 7131760 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7895. Min Range: -6.7895
Max Act: 5.9770. Min Act: -0.1700
Data Index: 3199588 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7895. Min Range: -6.7895
Max Act: 5.9770. Min Act: -0.1700
Data Index: 1612808 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7895. Min Range: -6.7895
Max Act: 5.9770. Min Act: -0.1700
Data Index: 3903658 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7895. Min Range: -6.7895
Max Act: 5.9457. Min Act: -0.1700
Data Index: 6299738 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7895. Min Range: -6.7895
Max Act: 5.9145. Min Act: -0.1700
Data Index: 1476964 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7895. Min Range: -6.7895
Max Act: 5.9457. Min Act: -0.1700
Data Index: 4077351 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19