Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.8260. Min Act: -0.1700
Data Index: 7625064 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.7322. Min Act: -0.1700
Data Index: 8665693 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.7009. Min Act: -0.1700
Data Index: 874072 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6696. Min Act: -0.1700
Data Index: 2976011 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6383. Min Act: -0.1700
Data Index: 907017 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6383. Min Act: -0.1700
Data Index: 6363911 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6383. Min Act: -0.1700
Data Index: 491869 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6383. Min Act: -0.1700
Data Index: 2426770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6383. Min Act: -0.1700
Data Index: 686268 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6383. Min Act: -0.1700
Data Index: 6000005 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6383. Min Act: -0.1700
Data Index: 3373940 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6383. Min Act: -0.1700
Data Index: 2995462 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6070. Min Act: -0.1700
Data Index: 6014564 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6070. Min Act: -0.1700
Data Index: 2505211 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6070. Min Act: -0.1700
Data Index: 6315965 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6070. Min Act: -0.1700
Data Index: 17208 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6070. Min Act: -0.1700
Data Index: 2593165 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6070. Min Act: -0.1700
Data Index: 2713120 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6070. Min Act: -0.1700
Data Index: 6893251 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8260. Min Range: -3.8260
Max Act: 3.6070. Min Act: -0.1700
Data Index: 141347 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19