Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0701. Min Range: -6.0701
Max Act: 6.0701. Min Act: -0.1700
Data Index: 8746132 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.9139. Min Act: -0.1700
Data Index: 3802218 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.7889. Min Act: -0.1700
Data Index: 7586043 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.7264. Min Act: -0.1700
Data Index: 3030151 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.7576. Min Act: -0.1700
Data Index: 7590025 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6951. Min Act: -0.1700
Data Index: 1519135 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6639. Min Act: -0.1700
Data Index: 1474246 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6639. Min Act: -0.1700
Data Index: 7165311 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6951. Min Act: -0.1700
Data Index: 707260 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6951. Min Act: -0.1700
Data Index: 6012511 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6639. Min Act: -0.1700
Data Index: 2570155 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6639. Min Act: -0.1700
Data Index: 1268824 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6326. Min Act: -0.1700
Data Index: 8369913 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.6014. Min Act: -0.1700
Data Index: 3904434 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.5701. Min Act: -0.1700
Data Index: 2793529 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.5701. Min Act: -0.1700
Data Index: 3203227 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.5076. Min Act: -0.1700
Data Index: 2627888 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.5076. Min Act: -0.1700
Data Index: 5077159 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.5076. Min Act: -0.1700
Data Index: 6374519 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0701. Min Range: -6.0701
Max Act: 5.5389. Min Act: -0.1700
Data Index: 4515817 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19