Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.9895. Min Act: -0.1700
Data Index: 7645812 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.9895. Min Act: -0.1700
Data Index: 5724040 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.8020. Min Act: -0.1700
Data Index: 5112830 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.7395. Min Act: -0.1700
Data Index: 5140274 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.6770. Min Act: -0.1700
Data Index: 1814784 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.6145. Min Act: -0.1700
Data Index: 6756005 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.5520. Min Act: -0.1700
Data Index: 690734 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.5520. Min Act: -0.1700
Data Index: 65187 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.4895. Min Act: -0.1700
Data Index: 1064121 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.4895. Min Act: -0.1700
Data Index: 6627741 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.4270. Min Act: -0.1700
Data Index: 2500800 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.4270. Min Act: -0.1700
Data Index: 7382699 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.3645. Min Act: -0.1700
Data Index: 4832556 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.3645. Min Act: -0.1700
Data Index: 1283490 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.3645. Min Act: -0.1700
Data Index: 6122501 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.3020. Min Act: -0.1700
Data Index: 6627743 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.3020. Min Act: -0.1700
Data Index: 5651481 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.3645. Min Act: -0.1700
Data Index: 4046648 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.3645. Min Act: -0.1700
Data Index: 5038335 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9895. Min Range: -8.9895
Max Act: 8.3645. Min Act: -0.1700
Data Index: 7168356 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19