Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.6141. Min Act: -0.1700
Data Index: 1126355 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.4579. Min Act: -0.1700
Data Index: 7856844 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3641. Min Act: -0.1700
Data Index: 4147319 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3641. Min Act: -0.1700
Data Index: 1794900 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3641. Min Act: -0.1700
Data Index: 2493728 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3016. Min Act: -0.1700
Data Index: 710928 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3016. Min Act: -0.1700
Data Index: 1913652 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3016. Min Act: -0.1700
Data Index: 3842943 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3329. Min Act: -0.1700
Data Index: 2791150 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3016. Min Act: -0.1700
Data Index: 314236 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.3016. Min Act: -0.1700
Data Index: 1962852 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.2704. Min Act: -0.1700
Data Index: 198041 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.2704. Min Act: -0.1700
Data Index: 2575013 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.2079. Min Act: -0.1700
Data Index: 4005989 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.2391. Min Act: -0.1700
Data Index: 3765505 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.2704. Min Act: -0.1700
Data Index: 6218363 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.1766. Min Act: -0.1700
Data Index: 852634 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.2079. Min Act: -0.1700
Data Index: 6971284 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.1454. Min Act: -0.1700
Data Index: 1767131 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6141. Min Range: -7.6141
Max Act: 7.1766. Min Act: -0.1700
Data Index: 1998528 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19