Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1044 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3941. Min Range: -5.3941
Max Act: 5.3941. Min Act: -0.1700
Data Index: 947654 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3941. Min Range: -5.3941
Max Act: 5.1441. Min Act: -0.1700
Data Index: 5997030 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3941. Min Range: -5.3941
Max Act: 5.1129. Min Act: -0.1700
Data Index: 7269451 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3941. Min Range: -5.3941
Max Act: 5.0504. Min Act: -0.1700
Data Index: 1407145 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3941. Min Range: -5.3941
Max Act: 5.0191. Min Act: -0.1700
Data Index: 7759597 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3941. Min Range: -5.3941
Max Act: 5.0504. Min Act: -0.1700
Data Index: 3971828 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3941. Min Range: -5.3941
Max Act: 5.0191. Min Act: -0.1700
Data Index: 5887733 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.9879. Min Act: -0.1700
Data Index: 4012692 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.9879. Min Act: -0.1700
Data Index: 2197991 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.9879. Min Act: -0.1700
Data Index: 1465399 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.9566. Min Act: -0.1700
Data Index: 279882 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.9566. Min Act: -0.1700
Data Index: 2213288 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.8941. Min Act: -0.1700
Data Index: 2388740 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.8629. Min Act: -0.1700
Data Index: 348333 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.8941. Min Act: -0.1700
Data Index: 2197981 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.8629. Min Act: -0.1700
Data Index: 8423424 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.8629. Min Act: -0.1700
Data Index: 8208749 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.8629. Min Act: -0.1700
Data Index: 4110062 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.8629. Min Act: -0.1700
Data Index: 919614 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3941. Min Range: -5.3941
Max Act: 4.8004. Min Act: -0.1700
Data Index: 4012695 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19