Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0094. Min Range: -5.0094
Max Act: 5.0094. Min Act: -0.1700
Data Index: 4118266 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.6657. Min Act: -0.1700
Data Index: 7368862 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.6344. Min Act: -0.1700
Data Index: 150089 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.6344. Min Act: -0.1700
Data Index: 2962635 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.6344. Min Act: -0.1700
Data Index: 120859 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.6032. Min Act: -0.1700
Data Index: 4913232 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.6032. Min Act: -0.1700
Data Index: 3319542 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.6032. Min Act: -0.1700
Data Index: 2147567 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.6032. Min Act: -0.1700
Data Index: 7273841 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5719. Min Act: -0.1700
Data Index: 948053 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5719. Min Act: -0.1700
Data Index: 4467924 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5407. Min Act: -0.1700
Data Index: 3831605 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5719. Min Act: -0.1700
Data Index: 8696899 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 6597359 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 1024587 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 6701638 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 3097923 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 4938030 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 1731359 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0094. Min Range: -5.0094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 3013761 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19