Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3793 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.3657. Min Act: -0.1700
Data Index: 5934929 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.3344. Min Act: -0.1700
Data Index: 5308319 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.1469. Min Act: -0.1700
Data Index: 6139817 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.1469. Min Act: -0.1700
Data Index: 5759150 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.1157. Min Act: -0.1700
Data Index: 4866071 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0844. Min Act: -0.1700
Data Index: 798012 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0844. Min Act: -0.1700
Data Index: 6667352 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0219. Min Act: -0.1700
Data Index: 1610447 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0532. Min Act: -0.1700
Data Index: 7793032 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0532. Min Act: -0.1700
Data Index: 4195723 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0219. Min Act: -0.1700
Data Index: 7793028 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0219. Min Act: -0.1700
Data Index: 8619680 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9594. Min Act: -0.1700
Data Index: 15554 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9907. Min Act: -0.1700
Data Index: 1266486 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9594. Min Act: -0.1700
Data Index: 3213830 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9594. Min Act: -0.1700
Data Index: 6167214 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9594. Min Act: -0.1700
Data Index: 2466625 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9594. Min Act: -0.1699
Data Index: 2368641 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9594. Min Act: -0.1700
Data Index: 1959237 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.8969. Min Act: -0.1700
Data Index: 4861890 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19