Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.9183. Min Act: -0.1700
Data Index: 8349279 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.6371. Min Act: -0.1700
Data Index: 7145829 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.5746. Min Act: -0.1700
Data Index: 221868 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.4808. Min Act: -0.1700
Data Index: 905866 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.4183. Min Act: -0.1700
Data Index: 4488487 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.3558. Min Act: -0.1700
Data Index: 5716788 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.2933. Min Act: -0.1700
Data Index: 5493009 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.2308. Min Act: -0.1700
Data Index: 8210865 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.1996. Min Act: -0.1700
Data Index: 7282998 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.1371. Min Act: -0.1700
Data Index: 3801942 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.1371. Min Act: -0.1700
Data Index: 3943371 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.1371. Min Act: -0.1700
Data Index: 3801943 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.1058. Min Act: -0.1700
Data Index: 7341674 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.0746. Min Act: -0.1700
Data Index: 3665094 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9183. Min Range: -6.9183
Max Act: 6.0746. Min Act: -0.1700
Data Index: 4416329 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9183. Min Range: -6.9183
Max Act: 5.9496. Min Act: -0.1700
Data Index: 5465909 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9183. Min Range: -6.9183
Max Act: 5.9183. Min Act: -0.1700
Data Index: 2657072 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9183. Min Range: -6.9183
Max Act: 5.9183. Min Act: -0.1700
Data Index: 1463890 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9183. Min Range: -6.9183
Max Act: 5.8871. Min Act: -0.1700
Data Index: 389316 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9183. Min Range: -6.9183
Max Act: 5.8558. Min Act: -0.1700
Data Index: 7773272 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19