Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.6072. Min Act: -0.1700
Data Index: 2289567 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.6072. Min Act: -0.1700
Data Index: 4164046 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.5588. Min Act: -0.1700
Data Index: 6596613 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.5427. Min Act: -0.1700
Data Index: 690512 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.5265. Min Act: -0.1700
Data Index: 8197160 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.5103. Min Act: -0.1700
Data Index: 5712877 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.5103. Min Act: -0.1700
Data Index: 890269 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4941. Min Act: -0.1700
Data Index: 4966049 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4941. Min Act: -0.1700
Data Index: 4214863 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.5103. Min Act: -0.1700
Data Index: 4375736 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4941. Min Act: -0.1700
Data Index: 1839733 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4941. Min Act: -0.1700
Data Index: 4383688 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4941. Min Act: -0.1700
Data Index: 1366441 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4779. Min Act: -0.1700
Data Index: 375498 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4941. Min Act: -0.1700
Data Index: 3001879 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.5103. Min Act: -0.1700
Data Index: 1079831 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4779. Min Act: -0.1700
Data Index: 4221591 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4779. Min Act: -0.1700
Data Index: 6214170 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4779. Min Act: -0.1700
Data Index: 2031433 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6072. Min Range: -2.6072
Max Act: 2.4779. Min Act: -0.1700
Data Index: 4375738 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19