Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1256 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.3941. Min Act: -0.1700
Data Index: 3344148 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.3316. Min Act: -0.1700
Data Index: 8358437 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.3316. Min Act: -0.1700
Data Index: 3898720 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.2691. Min Act: -0.1700
Data Index: 5254961 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.2691. Min Act: -0.1700
Data Index: 3613629 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.2691. Min Act: -0.1700
Data Index: 4732515 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.2378. Min Act: -0.1700
Data Index: 3153516 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.1753. Min Act: -0.1700
Data Index: 3215628 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.1441. Min Act: -0.1700
Data Index: 5123207 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.1753. Min Act: -0.1700
Data Index: 7389494 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.1441. Min Act: -0.1700
Data Index: 6047524 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.1128. Min Act: -0.1700
Data Index: 7693682 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.1128. Min Act: -0.1700
Data Index: 1877226 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.0503. Min Act: -0.1700
Data Index: 4086305 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.0503. Min Act: -0.1700
Data Index: 2036383 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3941. Min Range: -7.3941
Max Act: 7.0191. Min Act: -0.1700
Data Index: 3695544 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3941. Min Range: -7.3941
Max Act: 6.9878. Min Act: -0.1700
Data Index: 4462253 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3941. Min Range: -7.3941
Max Act: 6.9878. Min Act: -0.1700
Data Index: 1169804 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3941. Min Range: -7.3941
Max Act: 6.9566. Min Act: -0.1700
Data Index: 5134514 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3941. Min Range: -7.3941
Max Act: 6.9566. Min Act: -0.1700
Data Index: 1836000 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19