Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0626. Min Range: -5.0626
Max Act: 5.0626. Min Act: -0.1700
Data Index: 3862801 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0626. Min Range: -5.0626
Max Act: 5.0313. Min Act: -0.1700
Data Index: 1435857 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0626. Min Range: -5.0626
Max Act: 5.0001. Min Act: -0.1700
Data Index: 5257167 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0626. Min Range: -5.0626
Max Act: 5.0001. Min Act: -0.1700
Data Index: 1934313 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0626. Min Range: -5.0626
Max Act: 5.0001. Min Act: -0.1700
Data Index: 4481021 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0626. Min Range: -5.0626
Max Act: 5.0001. Min Act: -0.1700
Data Index: 4125862 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9688. Min Act: -0.1700
Data Index: 7162226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1700
Data Index: 3751729 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9688. Min Act: -0.1700
Data Index: 7780421 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9688. Min Act: -0.1700
Data Index: 3895648 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1700
Data Index: 2577547 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9688. Min Act: -0.1700
Data Index: 177115 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1700
Data Index: 5989724 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1698
Data Index: 5280019 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1700
Data Index: 1933751 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1700
Data Index: 5174394 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1700
Data Index: 7475293 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1700
Data Index: 3808084 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9376. Min Act: -0.1700
Data Index: 5735628 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9063. Min Act: -0.1700
Data Index: 3385133 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19