Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1189 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0626. Min Range: -7.0626
Max Act: 7.0626. Min Act: -0.1700
Data Index: 132283 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0626. Min Range: -7.0626
Max Act: 7.0313. Min Act: -0.1700
Data Index: 2968304 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0626. Min Range: -7.0626
Max Act: 7.0001. Min Act: -0.1700
Data Index: 7331434 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0626. Min Range: -7.0626
Max Act: 7.0001. Min Act: -0.1700
Data Index: 6231449 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0626. Min Range: -7.0626
Max Act: 7.0001. Min Act: -0.1700
Data Index: 1280329 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.9688. Min Act: -0.1700
Data Index: 4619545 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.9688. Min Act: -0.1700
Data Index: 7748415 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.9376. Min Act: -0.1700
Data Index: 5395138 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.9063. Min Act: -0.1700
Data Index: 5658516 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.9063. Min Act: -0.1700
Data Index: 1565952 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.9063. Min Act: -0.1700
Data Index: 7720610 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.8751. Min Act: -0.1700
Data Index: 678559 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.8751. Min Act: -0.1700
Data Index: 5836777 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.8751. Min Act: -0.1700
Data Index: 4656890 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.9063. Min Act: -0.1700
Data Index: 6198460 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.8751. Min Act: -0.1700
Data Index: 680111 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.8438. Min Act: -0.1700
Data Index: 3612317 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.8438. Min Act: -0.1700
Data Index: 4268055 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.8438. Min Act: -0.1700
Data Index: 7471618 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0626. Min Range: -7.0626
Max Act: 6.8438. Min Act: -0.1700
Data Index: 4245017 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19