Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0834. Min Range: -6.0834
Max Act: 6.0521. Min Act: -0.1700
Data Index: 6818693 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0834. Min Range: -6.0834
Max Act: 6.0521. Min Act: -0.1700
Data Index: 1241367 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0834. Min Range: -6.0834
Max Act: 6.0521. Min Act: -0.1700
Data Index: 2769687 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0834. Min Range: -6.0834
Max Act: 6.0834. Min Act: -0.1700
Data Index: 6577437 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.9896. Min Act: -0.1700
Data Index: 8151082 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.9271. Min Act: -0.1700
Data Index: 6549152 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.8959. Min Act: -0.1700
Data Index: 8137150 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.9584. Min Act: -0.1700
Data Index: 4267122 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.8646. Min Act: -0.1700
Data Index: 8650374 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.8646. Min Act: -0.1700
Data Index: 1997201 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.8646. Min Act: -0.1700
Data Index: 1241368 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.8334. Min Act: -0.1700
Data Index: 1642257 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.8334. Min Act: -0.1700
Data Index: 2148221 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.7709. Min Act: -0.1700
Data Index: 4394711 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.8334. Min Act: -0.1700
Data Index: 8517473 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.7709. Min Act: -0.1700
Data Index: 4533118 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.7709. Min Act: -0.1700
Data Index: 5064120 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.8021. Min Act: -0.1700
Data Index: 8608173 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.7084. Min Act: -0.1700
Data Index: 4730968 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0834. Min Range: -6.0834
Max Act: 5.7396. Min Act: -0.1700
Data Index: 70624 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19