Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5392 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.2674. Min Act: -0.1700
Data Index: 7005573 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1111. Min Act: -0.1700
Data Index: 8521486 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0799. Min Act: -0.1700
Data Index: 8729681 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1111. Min Act: -0.1700
Data Index: 3045833 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1111. Min Act: -0.1700
Data Index: 7217398 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1111. Min Act: -0.1700
Data Index: 2308084 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1111. Min Act: -0.1700
Data Index: 2921870 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0799. Min Act: -0.1700
Data Index: 4963472 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1111. Min Act: -0.1700
Data Index: 2620103 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0486. Min Act: -0.1700
Data Index: 2636820 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0486. Min Act: -0.1700
Data Index: 3114554 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 1880656 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0486. Min Act: -0.1700
Data Index: 7020401 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0486. Min Act: -0.1700
Data Index: 6633933 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 5541086 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 472489 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 4970033 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 7303005 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 4423842 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 8171894 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19