Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 424 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.5128. Min Act: -0.1700
Data Index: 3145152 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.3878. Min Act: -0.1700
Data Index: 5921919 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.3253. Min Act: -0.1700
Data Index: 396382 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.2628. Min Act: -0.1700
Data Index: 748813 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.2628. Min Act: -0.1700
Data Index: 4048777 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.2628. Min Act: -0.1700
Data Index: 305936 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.2003. Min Act: -0.1700
Data Index: 7852881 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.2628. Min Act: -0.1700
Data Index: 5764711 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.2003. Min Act: -0.1700
Data Index: 5392392 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.1378. Min Act: -0.1700
Data Index: 7059929 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.1378. Min Act: -0.1700
Data Index: 5293384 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.1378. Min Act: -0.1700
Data Index: 650951 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.0753. Min Act: -0.1700
Data Index: 394672 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.0753. Min Act: -0.1700
Data Index: 1163451 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.0128. Min Act: -0.1700
Data Index: 8729236 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.0753. Min Act: -0.1700
Data Index: 3747718 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.0128. Min Act: -0.1700
Data Index: 7107890 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5128. Min Range: -8.5128
Max Act: 7.9503. Min Act: -0.1700
Data Index: 356805 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.0128. Min Act: -0.1700
Data Index: 7905548 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5128. Min Range: -8.5128
Max Act: 8.0128. Min Act: -0.1700
Data Index: 3205994 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19