Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5306 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0595. Min Range: -9.0595
Max Act: 9.0595. Min Act: -0.1700
Data Index: 2724667 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0595. Min Range: -9.0595
Max Act: 8.0595. Min Act: -0.1700
Data Index: 882315 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.9658. Min Act: -0.1700
Data Index: 3368751 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.8095. Min Act: -0.1700
Data Index: 1834744 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.7783. Min Act: -0.1700
Data Index: 5450978 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.6845. Min Act: -0.1700
Data Index: 3528552 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.6220. Min Act: -0.1700
Data Index: 7546570 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.6220. Min Act: -0.1700
Data Index: 5857593 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.5908. Min Act: -0.1700
Data Index: 7057125 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.6220. Min Act: -0.1700
Data Index: 7078945 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.6220. Min Act: -0.1700
Data Index: 5518136 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.5595. Min Act: -0.1700
Data Index: 7496991 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.5595. Min Act: -0.1700
Data Index: 6786331 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.5283. Min Act: -0.1700
Data Index: 5457278 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.5595. Min Act: -0.1700
Data Index: 5807746 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.5595. Min Act: -0.1700
Data Index: 674549 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.4970. Min Act: -0.1700
Data Index: 7704177 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.4970. Min Act: -0.1700
Data Index: 3423849 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.4970. Min Act: -0.1700
Data Index: 3578706 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0595. Min Range: -9.0595
Max Act: 7.4658. Min Act: -0.1700
Data Index: 109605 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19