Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.2010. Min Act: -0.1700
Data Index: 3209311 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.1697. Min Act: -0.1700
Data Index: 7086393 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.1072. Min Act: -0.1700
Data Index: 6583773 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.1072. Min Act: -0.1700
Data Index: 57092 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0760. Min Act: -0.1700
Data Index: 2050890 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.1072. Min Act: -0.1700
Data Index: 4070946 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0447. Min Act: -0.1700
Data Index: 7857419 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0447. Min Act: -0.1700
Data Index: 6017120 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0447. Min Act: -0.1700
Data Index: 7548038 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0134. Min Act: -0.1700
Data Index: 6450400 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0134. Min Act: -0.1700
Data Index: 1765187 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0134. Min Act: -0.1700
Data Index: 2958058 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0134. Min Act: -0.1700
Data Index: 1870420 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2010. Min Range: -4.2010
Max Act: 3.9822. Min Act: -0.1700
Data Index: 454666 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0447. Min Act: -0.1700
Data Index: 4285937 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0134. Min Act: -0.1700
Data Index: 20331 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2010. Min Range: -4.2010
Max Act: 4.0134. Min Act: -0.1700
Data Index: 3679242 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2010. Min Range: -4.2010
Max Act: 3.9509. Min Act: -0.1700
Data Index: 526311 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2010. Min Range: -4.2010
Max Act: 3.9822. Min Act: -0.1700
Data Index: 3142410 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2010. Min Range: -4.2010
Max Act: 3.9509. Min Act: -0.1700
Data Index: 3942067 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19