Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.8978. Min Act: -0.1700
Data Index: 4595213 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.9603. Min Act: -0.1700
Data Index: 1093251 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.8665. Min Act: -0.1700
Data Index: 5038168 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.8665. Min Act: -0.1700
Data Index: 7732729 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.8353. Min Act: -0.1700
Data Index: 8694583 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.8040. Min Act: -0.1700
Data Index: 2042152 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.8040. Min Act: -0.1700
Data Index: 863932 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.7728. Min Act: -0.1700
Data Index: 1111204 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.7415. Min Act: -0.1700
Data Index: 7144397 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.7415. Min Act: -0.1700
Data Index: 5692044 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.7415. Min Act: -0.1700
Data Index: 6757976 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.7103. Min Act: -0.1700
Data Index: 6958951 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.7103. Min Act: -0.1700
Data Index: 1189824 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.6790. Min Act: -0.1700
Data Index: 5969298 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.6478. Min Act: -0.1700
Data Index: 4151341 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.6790. Min Act: -0.1700
Data Index: 7420163 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.6790. Min Act: -0.1700
Data Index: 7057157 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.6790. Min Act: -0.1700
Data Index: 227190 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.6478. Min Act: -0.1700
Data Index: 3491433 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9603. Min Range: -5.9603
Max Act: 5.6478. Min Act: -0.1700
Data Index: 5045170 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19