Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.8814. Min Act: -0.1700
Data Index: 5966607 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.8501. Min Act: -0.1700
Data Index: 1122163 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7876. Min Act: -0.1700
Data Index: 6954466 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7876. Min Act: -0.1700
Data Index: 2325104 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7876. Min Act: -0.1700
Data Index: 8712178 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7564. Min Act: -0.1700
Data Index: 2630102 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7564. Min Act: -0.1700
Data Index: 5479603 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7251. Min Act: -0.1700
Data Index: 6798877 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7251. Min Act: -0.1700
Data Index: 4442858 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7251. Min Act: -0.1700
Data Index: 4442856 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7251. Min Act: -0.1700
Data Index: 2301178 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7251. Min Act: -0.1700
Data Index: 7205691 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7251. Min Act: -0.1700
Data Index: 4848568 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7251. Min Act: -0.1700
Data Index: 3658291 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.7251. Min Act: -0.1700
Data Index: 1569253 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.6939. Min Act: -0.1700
Data Index: 37377 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.6939. Min Act: -0.1700
Data Index: 5789981 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.6939. Min Act: -0.1700
Data Index: 4315169 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.6939. Min Act: -0.1700
Data Index: 113335 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8814. Min Range: -5.8814
Max Act: 5.6939. Min Act: -0.1700
Data Index: 6587712 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19