Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.1056. Min Act: -0.1700
Data Index: 25411 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0744. Min Act: -0.1700
Data Index: 3315503 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0744. Min Act: -0.1700
Data Index: 8689599 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0744. Min Act: -0.1700
Data Index: 5854564 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0431. Min Act: -0.1700
Data Index: 3306598 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0744. Min Act: -0.1700
Data Index: 8463433 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0431. Min Act: -0.1700
Data Index: 8658874 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0119. Min Act: -0.1700
Data Index: 2023855 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1056. Min Range: -5.1056
Max Act: 4.9806. Min Act: -0.1700
Data Index: 2558664 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0119. Min Act: -0.1700
Data Index: 4574451 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0119. Min Act: -0.1700
Data Index: 1944903 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0119. Min Act: -0.1700
Data Index: 3805821 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0119. Min Act: -0.1700
Data Index: 5261055 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0119. Min Act: -0.1700
Data Index: 1024068 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0119. Min Act: -0.1700
Data Index: 2074378 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1056. Min Range: -5.1056
Max Act: 5.0119. Min Act: -0.1700
Data Index: 1114466 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1056. Min Range: -5.1056
Max Act: 4.9806. Min Act: -0.1700
Data Index: 604389 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1056. Min Range: -5.1056
Max Act: 4.9806. Min Act: -0.1700
Data Index: 2764256 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1056. Min Range: -5.1056
Max Act: 4.9806. Min Act: -0.1700
Data Index: 3143849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1056. Min Range: -5.1056
Max Act: 4.9806. Min Act: -0.1700
Data Index: 4753356 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19