Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4493. Min Range: -9.4493
Max Act: 9.4493. Min Act: -0.1700
Data Index: 2761451 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4493. Min Range: -9.4493
Max Act: 9.1368. Min Act: -0.1700
Data Index: 4608636 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4493. Min Range: -9.4493
Max Act: 9.1368. Min Act: -0.1700
Data Index: 2761452 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4493. Min Range: -9.4493
Max Act: 9.0118. Min Act: -0.1700
Data Index: 6659893 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.9493. Min Act: -0.1700
Data Index: 1310750 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.8243. Min Act: -0.1699
Data Index: 8316477 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.6993. Min Act: -0.1700
Data Index: 7608871 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.7618. Min Act: -0.1700
Data Index: 3996269 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.5743. Min Act: -0.1700
Data Index: 7336029 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.5743. Min Act: -0.1700
Data Index: 1541242 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.4493. Min Act: -0.1700
Data Index: 3547510 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.4493. Min Act: -0.1700
Data Index: 915837 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.3868. Min Act: -0.1700
Data Index: 5200279 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.3868. Min Act: -0.1700
Data Index: 7911990 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.4493. Min Act: -0.1700
Data Index: 7830560 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.3868. Min Act: -0.1700
Data Index: 2984233 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.3868. Min Act: -0.1700
Data Index: 3889414 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.3243. Min Act: -0.1700
Data Index: 4950456 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.3243. Min Act: -0.1700
Data Index: 5048511 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4493. Min Range: -9.4493
Max Act: 8.3243. Min Act: -0.1700
Data Index: 4004769 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19