Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.9082. Min Act: -0.1700
Data Index: 979732 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.8769. Min Act: -0.1700
Data Index: 2010666 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.7519. Min Act: -0.1700
Data Index: 8249563 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.7519. Min Act: -0.1700
Data Index: 1887469 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.7519. Min Act: -0.1700
Data Index: 533952 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.7207. Min Act: -0.1700
Data Index: 8440846 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6894. Min Act: -0.1700
Data Index: 3199285 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6894. Min Act: -0.1700
Data Index: 601840 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6894. Min Act: -0.1700
Data Index: 6869031 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6894. Min Act: -0.1700
Data Index: 8309030 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6582. Min Act: -0.1700
Data Index: 5775467 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6582. Min Act: -0.1700
Data Index: 1447669 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6582. Min Act: -0.1700
Data Index: 7309419 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6582. Min Act: -0.1700
Data Index: 2072155 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6582. Min Act: -0.1700
Data Index: 6339329 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6269. Min Act: -0.1700
Data Index: 6827542 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6269. Min Act: -0.1700
Data Index: 1584901 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6269. Min Act: -0.1700
Data Index: 5859707 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.6269. Min Act: -0.1700
Data Index: 3397895 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.5957. Min Act: -0.1700
Data Index: 7657881 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19