Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 3155843 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 3063530 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 343754 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 1211385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 6609929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 6314341 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 116637 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 8462882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 6225348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 7310895 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 7542515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 985636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 3859359 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 8412971 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 3798917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 2104747 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 7043927 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 3446264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 4332367 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0266. Min Range: -5.0266
Max Act: 5.0266. Min Act: -0.1700
Data Index: 8076792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19