Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.3701. Min Act: -0.1700
Data Index: 837867 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.3701. Min Act: -0.1700
Data Index: 4153609 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.3076. Min Act: -0.1700
Data Index: 8211441 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.3076. Min Act: -0.1700
Data Index: 821638 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.3076. Min Act: -0.1700
Data Index: 8276799 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.3076. Min Act: -0.1700
Data Index: 7989618 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.2763. Min Act: -0.1700
Data Index: 5422112 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.2451. Min Act: -0.1700
Data Index: 7607580 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.1826. Min Act: -0.1700
Data Index: 4974754 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.1201. Min Act: -0.1700
Data Index: 5127963 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.1513. Min Act: -0.1700
Data Index: 8256355 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.0888. Min Act: -0.1700
Data Index: 8482235 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.0888. Min Act: -0.1700
Data Index: 7241469 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.0888. Min Act: -0.1700
Data Index: 4135448 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.0888. Min Act: -0.1700
Data Index: 1950080 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3701. Min Range: -6.3701
Max Act: 6.0263. Min Act: -0.1700
Data Index: 984922 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3701. Min Range: -6.3701
Max Act: 5.9638. Min Act: -0.1700
Data Index: 1701806 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3701. Min Range: -6.3701
Max Act: 5.9951. Min Act: -0.1700
Data Index: 6891833 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3701. Min Range: -6.3701
Max Act: 5.9951. Min Act: -0.1700
Data Index: 5298827 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3701. Min Range: -6.3701
Max Act: 5.9951. Min Act: -0.1700
Data Index: 1705408 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19