Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.6533. Min Act: -0.1700
Data Index: 8795298 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.6533. Min Act: -0.1700
Data Index: 4884801 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.3408. Min Act: -0.1700
Data Index: 5902840 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2783. Min Act: -0.1700
Data Index: 7224974 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2783. Min Act: -0.1700
Data Index: 6039255 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2783. Min Act: -0.1700
Data Index: 2090514 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2783. Min Act: -0.1700
Data Index: 1862186 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2158. Min Act: -0.1700
Data Index: 2786670 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2158. Min Act: -0.1700
Data Index: 94120 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2158. Min Act: -0.1700
Data Index: 7492932 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2158. Min Act: -0.1700
Data Index: 3571194 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.2158. Min Act: -0.1700
Data Index: 6757946 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.1533. Min Act: -0.1700
Data Index: 5734520 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.1533. Min Act: -0.1700
Data Index: 8092364 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.1533. Min Act: -0.1700
Data Index: 3999020 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.0908. Min Act: -0.1700
Data Index: 6970792 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.0283. Min Act: -0.1700
Data Index: 8306566 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.0908. Min Act: -0.1700
Data Index: 5223054 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.0908. Min Act: -0.1700
Data Index: 3852914 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6533. Min Range: -9.6533
Max Act: 9.0908. Min Act: -0.1700
Data Index: 3453126 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19