Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.7637. Min Act: -0.1700
Data Index: 211947 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6386. Min Act: -0.1700
Data Index: 4718197 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6386. Min Act: -0.1700
Data Index: 6025624 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5916. Min Act: -0.1700
Data Index: 1526051 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5916. Min Act: -0.1700
Data Index: 2573216 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5916. Min Act: -0.1700
Data Index: 4838404 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5760. Min Act: -0.1700
Data Index: 6708526 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5760. Min Act: -0.1700
Data Index: 5563781 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5760. Min Act: -0.1700
Data Index: 5289622 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 6891306 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 2706607 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 3270277 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 1838453 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 4654851 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 2342622 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 6751630 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 6053075 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5603. Min Act: -0.1700
Data Index: 4721048 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5447. Min Act: -0.1700
Data Index: 4172489 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.5447. Min Act: -0.1700
Data Index: 5836233 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19