Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4749 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7578. Min Range: -8.7578
Max Act: 8.7578. Min Act: -0.1700
Data Index: 1843406 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7578. Min Range: -8.7578
Max Act: 8.3828. Min Act: -0.1700
Data Index: 8671624 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7578. Min Range: -8.7578
Max Act: 8.2578. Min Act: -0.1700
Data Index: 3599072 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7578. Min Range: -8.7578
Max Act: 8.2578. Min Act: -0.1700
Data Index: 8669447 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7578. Min Range: -8.7578
Max Act: 8.0390. Min Act: -0.1700
Data Index: 1291363 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7578. Min Range: -8.7578
Max Act: 8.0078. Min Act: -0.1700
Data Index: 7983257 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.9765. Min Act: -0.1700
Data Index: 6708450 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.9453. Min Act: -0.1700
Data Index: 2799245 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.9140. Min Act: -0.1700
Data Index: 4736151 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.9140. Min Act: -0.1700
Data Index: 7896572 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.8828. Min Act: -0.1700
Data Index: 5005539 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.8828. Min Act: -0.1700
Data Index: 695275 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.8828. Min Act: -0.1700
Data Index: 186824 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.8203. Min Act: -0.1700
Data Index: 1266420 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.8203. Min Act: -0.1700
Data Index: 553847 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.8203. Min Act: -0.1700
Data Index: 6427580 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.7578. Min Act: -0.1700
Data Index: 8122970 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.7890. Min Act: -0.1700
Data Index: 8777404 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.7265. Min Act: -0.1700
Data Index: 5927427 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7578. Min Range: -8.7578
Max Act: 7.7265. Min Act: -0.1700
Data Index: 623383 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19