Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1775. Min Range: -1.1775
Max Act: 1.1775. Min Act: -0.1700
Data Index: 183399 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1775. Min Range: -1.1775
Max Act: 1.0722. Min Act: -0.1698
Data Index: 2636863 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1775. Min Range: -1.1775
Max Act: 1.0199. Min Act: -0.1700
Data Index: 1635920 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1775. Min Range: -1.1775
Max Act: 1.0025. Min Act: -0.1700
Data Index: 1897959 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1775. Min Range: -1.1775
Max Act: 1.0025. Min Act: -0.1700
Data Index: 6219437 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.9852. Min Act: -0.1700
Data Index: 270016 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.9852. Min Act: -0.1695
Data Index: 1551831 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.9679. Min Act: -0.1699
Data Index: 895255 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.9506. Min Act: -0.1700
Data Index: 2935355 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.9162. Min Act: -0.1700
Data Index: 2958372 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.9076. Min Act: -0.1700
Data Index: 1151129 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.9076. Min Act: -0.1700
Data Index: 6623131 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.8905. Min Act: -0.1700
Data Index: 666787 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.9076. Min Act: -0.1700
Data Index: 5267863 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.8905. Min Act: -0.1700
Data Index: 8022808 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.8820. Min Act: -0.1700
Data Index: 780628 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.8820. Min Act: -0.1698
Data Index: 904746 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.8820. Min Act: -0.1700
Data Index: 1654211 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.8650. Min Act: -0.1700
Data Index: 5447245 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1775. Min Range: -1.1775
Max Act: 0.8735. Min Act: -0.1698
Data Index: 3114328 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19