Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4539 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.6142. Min Act: -0.1700
Data Index: 8058962 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.5829. Min Act: -0.1700
Data Index: 748360 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.3642. Min Act: -0.1700
Data Index: 2354785 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.3329. Min Act: -0.1700
Data Index: 6791876 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.2704. Min Act: -0.1700
Data Index: 3443788 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.2392. Min Act: -0.1700
Data Index: 4371837 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.1767. Min Act: -0.1700
Data Index: 1269905 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.1454. Min Act: -0.1700
Data Index: 2188864 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0829. Min Act: -0.1700
Data Index: 3352033 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.1142. Min Act: -0.1700
Data Index: 5195602 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.1142. Min Act: -0.1700
Data Index: 4910327 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0829. Min Act: -0.1700
Data Index: 3696510 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0829. Min Act: -0.1700
Data Index: 742799 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0829. Min Act: -0.1700
Data Index: 5415406 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0517. Min Act: -0.1700
Data Index: 385500 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0829. Min Act: -0.1700
Data Index: 6787815 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0517. Min Act: -0.1700
Data Index: 7862052 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0204. Min Act: -0.1700
Data Index: 6367451 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0204. Min Act: -0.1700
Data Index: 6320362 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6142. Min Range: -7.6142
Max Act: 7.0204. Min Act: -0.1700
Data Index: 5841041 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19