Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.7437. Min Act: -0.1700
Data Index: 6853092 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.6187. Min Act: -0.1700
Data Index: 1834836 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5874. Min Act: -0.1700
Data Index: 1268403 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5874. Min Act: -0.1700
Data Index: 8008716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5874. Min Act: -0.1700
Data Index: 1618754 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5874. Min Act: -0.1700
Data Index: 5998045 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5874. Min Act: -0.1700
Data Index: 442399 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 5594612 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 5255098 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 1912011 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 3976214 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 2206998 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 6873180 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5249. Min Act: -0.1700
Data Index: 584893 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 3386061 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 8036961 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 4658348 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 2423165 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5249. Min Act: -0.1700
Data Index: 1168398 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5249. Min Act: -0.1700
Data Index: 28430 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19