Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.8141. Min Act: -0.1700
Data Index: 7970217 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.4703. Min Act: -0.1700
Data Index: 1990510 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.4078. Min Act: -0.1700
Data Index: 4379319 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.3766. Min Act: -0.1700
Data Index: 3444493 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.3766. Min Act: -0.1700
Data Index: 1676616 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.3453. Min Act: -0.1700
Data Index: 7366296 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.3453. Min Act: -0.1700
Data Index: 7635028 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.3766. Min Act: -0.1700
Data Index: 1654928 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.2516. Min Act: -0.1700
Data Index: 2260665 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.2203. Min Act: -0.1700
Data Index: 2711041 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0953. Min Act: -0.1700
Data Index: 3294605 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0641. Min Act: -0.1700
Data Index: 6373737 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0641. Min Act: -0.1700
Data Index: 227008 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0328. Min Act: -0.1700
Data Index: 5921053 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0328. Min Act: -0.1700
Data Index: 447476 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0016. Min Act: -0.1700
Data Index: 7547270 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0016. Min Act: -0.1700
Data Index: 850483 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0016. Min Act: -0.1700
Data Index: 1760507 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8141. Min Range: -7.8141
Max Act: 7.0016. Min Act: -0.1700
Data Index: 1702324 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8141. Min Range: -7.8141
Max Act: 6.9703. Min Act: -0.1700
Data Index: 4308683 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19