Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.7987. Min Act: -0.1700
Data Index: 7458996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.7048. Min Act: -0.1700
Data Index: 7446342 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.7048. Min Act: -0.1700
Data Index: 7162950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.7361. Min Act: -0.1700
Data Index: 5213701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6735. Min Act: -0.1700
Data Index: 6296428 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6735. Min Act: -0.1700
Data Index: 5807186 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6735. Min Act: -0.1700
Data Index: 3853354 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6735. Min Act: -0.1700
Data Index: 458074 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6735. Min Act: -0.1700
Data Index: 1827592 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6735. Min Act: -0.1700
Data Index: 3490127 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 3616903 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 179776 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 701539 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 2096474 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 3587948 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 4020789 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 4322401 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 1037822 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 5455970 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7987. Min Range: -3.7987
Max Act: 3.6422. Min Act: -0.1700
Data Index: 1700093 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19