Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2015. Min Range: -3.2015
Max Act: 3.2015. Min Act: -0.1700
Data Index: 491026 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2015. Min Range: -3.2015
Max Act: 3.2015. Min Act: -0.1700
Data Index: 4969836 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2015. Min Range: -3.2015
Max Act: 3.1228. Min Act: -0.1700
Data Index: 2064806 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2015. Min Range: -3.2015
Max Act: 3.0913. Min Act: -0.1700
Data Index: 5086730 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2015. Min Range: -3.2015
Max Act: 3.0281. Min Act: -0.1700
Data Index: 3763940 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2015. Min Range: -3.2015
Max Act: 3.0281. Min Act: -0.1700
Data Index: 5730024 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2015. Min Range: -3.2015
Max Act: 3.0124. Min Act: -0.1700
Data Index: 6586032 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2015. Min Range: -3.2015
Max Act: 3.0281. Min Act: -0.1700
Data Index: 8381571 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9965. Min Act: -0.1700
Data Index: 7528479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9807. Min Act: -0.1700
Data Index: 8250915 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9965. Min Act: -0.1700
Data Index: 4383846 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9649. Min Act: -0.1700
Data Index: 5187661 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9649. Min Act: -0.1700
Data Index: 4057031 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9649. Min Act: -0.1700
Data Index: 6674438 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9491. Min Act: -0.1700
Data Index: 1428660 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9491. Min Act: -0.1700
Data Index: 8372481 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9491. Min Act: -0.1700
Data Index: 7977365 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9491. Min Act: -0.1700
Data Index: 2245773 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9333. Min Act: -0.1700
Data Index: 1578642 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2015. Min Range: -3.2015
Max Act: 2.9333. Min Act: -0.1700
Data Index: 2933026 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19