Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.6517. Min Act: -0.1700
Data Index: 8201225 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5713. Min Act: -0.1700
Data Index: 3438863 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5713. Min Act: -0.1700
Data Index: 1544575 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5551. Min Act: -0.1700
Data Index: 6196482 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5551. Min Act: -0.1700
Data Index: 5270183 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5551. Min Act: -0.1700
Data Index: 5421240 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 1386858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 3807036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 3320003 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 4690994 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 4872952 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 2239293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 1623739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 5068895 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 3432896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 5125252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 3740874 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 4362310 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 2017119 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6517. Min Range: -2.6517
Max Act: 2.5390. Min Act: -0.1700
Data Index: 4466383 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19