Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1189. Min Range: -5.1189
Max Act: 5.1189. Min Act: -0.1700
Data Index: 4598785 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1189. Min Range: -5.1189
Max Act: 5.1189. Min Act: -0.1700
Data Index: 4598771 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1189. Min Range: -5.1189
Max Act: 5.0876. Min Act: -0.1700
Data Index: 4598772 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1189. Min Range: -5.1189
Max Act: 5.0564. Min Act: -0.1700
Data Index: 4598773 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1189. Min Range: -5.1189
Max Act: 5.0251. Min Act: -0.1700
Data Index: 4598778 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.9939. Min Act: -0.1700
Data Index: 4873042 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.9314. Min Act: -0.1700
Data Index: 4598777 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.8376. Min Act: -0.1700
Data Index: 1460333 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.8376. Min Act: -0.1700
Data Index: 4873040 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.8064. Min Act: -0.1700
Data Index: 1511800 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.6501. Min Act: -0.1700
Data Index: 2754146 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.6189. Min Act: -0.1700
Data Index: 4598783 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.5564. Min Act: -0.1700
Data Index: 4496239 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.6189. Min Act: -0.1700
Data Index: 4598786 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.5876. Min Act: -0.1700
Data Index: 4598780 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.5876. Min Act: -0.1700
Data Index: 4598782 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.5251. Min Act: -0.1700
Data Index: 4598789 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.4939. Min Act: -0.1700
Data Index: 835138 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.4939. Min Act: -0.1700
Data Index: 4598784 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1189. Min Range: -5.1189
Max Act: 4.4626. Min Act: -0.1700
Data Index: 4293111 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19