Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 611 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8481. Min Act: -0.1700
Data Index: 1621625 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8640. Min Act: -0.1700
Data Index: 7411956 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8322. Min Act: -0.1700
Data Index: 4662995 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8799. Min Act: -0.1700
Data Index: 7535616 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8640. Min Act: -0.1700
Data Index: 4061572 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8163. Min Act: -0.1700
Data Index: 2839691 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8163. Min Act: -0.1700
Data Index: 1952752 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8481. Min Act: -0.1700
Data Index: 8318184 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8004. Min Act: -0.1700
Data Index: 8819446 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8004. Min Act: -0.1700
Data Index: 2965309 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8004. Min Act: -0.1700
Data Index: 8237362 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8163. Min Act: -0.1700
Data Index: 5563436 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.7526. Min Act: -0.1700
Data Index: 6725151 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8004. Min Act: -0.1700
Data Index: 3970116 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8163. Min Act: -0.1700
Data Index: 7942154 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.7844. Min Act: -0.1700
Data Index: 7801009 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.7844. Min Act: -0.1700
Data Index: 3545015 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.7844. Min Act: -0.1700
Data Index: 7439505 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.8163. Min Act: -0.1700
Data Index: 2357667 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8799. Min Range: -2.8799
Max Act: 2.7844. Min Act: -0.1700
Data Index: 5796380 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19