Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4221 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2582. Min Range: -8.2582
Max Act: 8.2582. Min Act: -0.1700
Data Index: 6442424 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2582. Min Range: -8.2582
Max Act: 8.0707. Min Act: -0.1700
Data Index: 3581706 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2582. Min Range: -8.2582
Max Act: 8.0082. Min Act: -0.1700
Data Index: 5900729 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.9457. Min Act: -0.1700
Data Index: 3990083 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.9457. Min Act: -0.1700
Data Index: 5714618 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.8832. Min Act: -0.1700
Data Index: 5214797 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.7895. Min Act: -0.1700
Data Index: 5025550 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.7895. Min Act: -0.1700
Data Index: 1227217 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.7895. Min Act: -0.1700
Data Index: 3581705 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.7895. Min Act: -0.1700
Data Index: 7309575 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.7582. Min Act: -0.1700
Data Index: 5168448 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.7895. Min Act: -0.1700
Data Index: 5412885 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.7582. Min Act: -0.1700
Data Index: 4734184 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.6957. Min Act: -0.1700
Data Index: 518374 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.6957. Min Act: -0.1700
Data Index: 8713836 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.6645. Min Act: -0.1700
Data Index: 3688095 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.6645. Min Act: -0.1700
Data Index: 6340226 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.6645. Min Act: -0.1700
Data Index: 4368979 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.6645. Min Act: -0.1700
Data Index: 3078180 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2582. Min Range: -8.2582
Max Act: 7.6645. Min Act: -0.1700
Data Index: 683013 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19