Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.9975. Min Act: -0.1700
Data Index: 2388329 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.9975. Min Act: -0.1700
Data Index: 1733760 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.9038. Min Act: -0.1700
Data Index: 7827636 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.9038. Min Act: -0.1700
Data Index: 5977344 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.8413. Min Act: -0.1700
Data Index: 4627646 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.8100. Min Act: -0.1700
Data Index: 781131 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.7788. Min Act: -0.1700
Data Index: 8581315 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.7788. Min Act: -0.1700
Data Index: 5846699 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.7475. Min Act: -0.1700
Data Index: 5939956 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.7163. Min Act: -0.1700
Data Index: 5535072 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.7163. Min Act: -0.1700
Data Index: 889787 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.7163. Min Act: -0.1700
Data Index: 5038575 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.6850. Min Act: -0.1700
Data Index: 4478776 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.6850. Min Act: -0.1700
Data Index: 3312292 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.6538. Min Act: -0.1700
Data Index: 2538747 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.6850. Min Act: -0.1700
Data Index: 8497667 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.6850. Min Act: -0.1700
Data Index: 3065852 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.6850. Min Act: -0.1700
Data Index: 7128399 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.6850. Min Act: -0.1700
Data Index: 5840125 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9975. Min Range: -4.9975
Max Act: 4.7163. Min Act: -0.1700
Data Index: 5708953 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19