Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2121. Min Range: -7.2121
Max Act: 7.2121. Min Act: -0.1700
Data Index: 7898798 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.8059. Min Act: -0.1700
Data Index: 7010736 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.5246. Min Act: -0.1700
Data Index: 7980408 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.4934. Min Act: -0.1700
Data Index: 7151712 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.4621. Min Act: -0.1700
Data Index: 4003911 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.3684. Min Act: -0.1700
Data Index: 6589634 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.3371. Min Act: -0.1700
Data Index: 7316585 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.3059. Min Act: -0.1700
Data Index: 1352476 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2746. Min Act: -0.1700
Data Index: 705085 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2746. Min Act: -0.1700
Data Index: 1681597 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2746. Min Act: -0.1700
Data Index: 2595334 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2434. Min Act: -0.1700
Data Index: 4815496 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2434. Min Act: -0.1700
Data Index: 5694385 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2121. Min Act: -0.1700
Data Index: 3585681 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.1809. Min Act: -0.1700
Data Index: 3343969 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.1809. Min Act: -0.1700
Data Index: 4098587 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2121. Min Act: -0.1700
Data Index: 937308 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2121. Min Act: -0.1700
Data Index: 36874 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2121. Min Act: -0.1700
Data Index: 4750626 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2121. Min Range: -7.2121
Max Act: 6.2121. Min Act: -0.1700
Data Index: 4613186 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19