Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.8482. Min Act: -0.1700
Data Index: 4064594 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.7857. Min Act: -0.1700
Data Index: 7495959 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.7857. Min Act: -0.1700
Data Index: 2887479 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.6919. Min Act: -0.1700
Data Index: 3245905 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.6294. Min Act: -0.1700
Data Index: 4186728 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.4419. Min Act: -0.1700
Data Index: 8076330 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.4732. Min Act: -0.1700
Data Index: 3574399 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.4419. Min Act: -0.1700
Data Index: 3393366 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.4419. Min Act: -0.1700
Data Index: 3356649 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.4107. Min Act: -0.1700
Data Index: 7072025 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.3794. Min Act: -0.1700
Data Index: 8482260 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.3482. Min Act: -0.1700
Data Index: 5067625 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.3482. Min Act: -0.1700
Data Index: 2540617 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.3169. Min Act: -0.1700
Data Index: 3227841 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.2232. Min Act: -0.1700
Data Index: 3206825 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.1919. Min Act: -0.1700
Data Index: 3227842 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.0982. Min Act: -0.1700
Data Index: 2228887 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.1607. Min Act: -0.1700
Data Index: 2228893 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.0982. Min Act: -0.1700
Data Index: 2339498 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8482. Min Range: -7.8482
Max Act: 7.0982. Min Act: -0.1700
Data Index: 6768240 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19