Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1587. Min Range: -6.1587
Max Act: 6.1587. Min Act: -0.1700
Data Index: 6089117 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1587. Min Range: -6.1587
Max Act: 6.0025. Min Act: -0.1700
Data Index: 5845982 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.9712. Min Act: -0.1700
Data Index: 1040071 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.9400. Min Act: -0.1700
Data Index: 7962702 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.9400. Min Act: -0.1700
Data Index: 4944475 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.9087. Min Act: -0.1700
Data Index: 4718189 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.8775. Min Act: -0.1700
Data Index: 537895 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.8462. Min Act: -0.1700
Data Index: 6699277 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.8150. Min Act: -0.1700
Data Index: 180358 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.8150. Min Act: -0.1700
Data Index: 8065096 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.8150. Min Act: -0.1700
Data Index: 8084141 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.7837. Min Act: -0.1700
Data Index: 2117118 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.7837. Min Act: -0.1700
Data Index: 2320283 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.7837. Min Act: -0.1700
Data Index: 8389790 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.7525. Min Act: -0.1700
Data Index: 3757806 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.7525. Min Act: -0.1700
Data Index: 6089118 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.7525. Min Act: -0.1700
Data Index: 1251712 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.7212. Min Act: -0.1700
Data Index: 2171929 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.7212. Min Act: -0.1700
Data Index: 8069727 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1587. Min Range: -6.1587
Max Act: 5.6900. Min Act: -0.1700
Data Index: 3340689 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19