Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 731 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.7237. Min Act: -0.1700
Data Index: 2561735 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.7237. Min Act: -0.1700
Data Index: 1011793 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.6924. Min Act: -0.1700
Data Index: 7632100 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.6924. Min Act: -0.1700
Data Index: 7423971 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.6299. Min Act: -0.1700
Data Index: 5698450 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5987. Min Act: -0.1700
Data Index: 6308397 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5987. Min Act: -0.1700
Data Index: 4697342 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5674. Min Act: -0.1700
Data Index: 5424704 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5987. Min Act: -0.1700
Data Index: 3300879 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5674. Min Act: -0.1700
Data Index: 5754566 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5362. Min Act: -0.1700
Data Index: 122001 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5362. Min Act: -0.1700
Data Index: 1566305 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5362. Min Act: -0.1700
Data Index: 5754577 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.5049. Min Act: -0.1700
Data Index: 2045816 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.4737. Min Act: -0.1700
Data Index: 1467944 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.4737. Min Act: -0.1700
Data Index: 710679 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.4737. Min Act: -0.1700
Data Index: 872890 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.4737. Min Act: -0.1700
Data Index: 3048074 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.4424. Min Act: -0.1700
Data Index: 4582775 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7237. Min Range: -4.7237
Max Act: 4.4424. Min Act: -0.1700
Data Index: 436881 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19