Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4230 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1099. Min Range: -13.1099
Max Act: 13.1099. Min Act: -0.1700
Data Index: 1164370 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1099. Min Range: -13.1099
Max Act: 12.5474. Min Act: -0.1700
Data Index: 1871752 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1099. Min Range: -13.1099
Max Act: 12.3599. Min Act: -0.1700
Data Index: 3837214 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1099. Min Range: -13.1099
Max Act: 12.2974. Min Act: -0.1700
Data Index: 952751 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1099. Min Range: -13.1099
Max Act: 12.2349. Min Act: -0.1700
Data Index: 4096617 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1099. Min Range: -13.1099
Max Act: 12.2349. Min Act: -0.1700
Data Index: 3791876 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1099. Min Range: -13.1099
Max Act: 12.1099. Min Act: -0.1700
Data Index: 6927825 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1099. Min Range: -13.1099
Max Act: 12.0474. Min Act: -0.1700
Data Index: 5199747 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1099. Min Range: -13.1099
Max Act: 12.0474. Min Act: -0.1700
Data Index: 5002742 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.9849. Min Act: -0.1700
Data Index: 5981853 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.9849. Min Act: -0.1700
Data Index: 8081766 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.9849. Min Act: -0.1700
Data Index: 3069184 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.9849. Min Act: -0.1700
Data Index: 7085798 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.8599. Min Act: -0.1700
Data Index: 240520 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.8599. Min Act: -0.1700
Data Index: 7664006 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.8599. Min Act: -0.1700
Data Index: 7815435 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.8599. Min Act: -0.1700
Data Index: 6954141 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.8599. Min Act: -0.1700
Data Index: 8172435 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.7974. Min Act: -0.1700
Data Index: 4001617 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1099. Min Range: -13.1099
Max Act: 11.7974. Min Act: -0.1700
Data Index: 8095235 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19