Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3331 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.9952. Min Act: -0.1700
Data Index: 307528 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.9015. Min Act: -0.1700
Data Index: 7942776 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.8390. Min Act: -0.1700
Data Index: 1593024 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6827. Min Act: -0.1700
Data Index: 2387685 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6827. Min Act: -0.1700
Data Index: 8657580 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6202. Min Act: -0.1700
Data Index: 7129961 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5890. Min Act: -0.1700
Data Index: 4799816 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 316198 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5890. Min Act: -0.1700
Data Index: 1659765 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 5678625 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 6256949 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 7022936 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5890. Min Act: -0.1700
Data Index: 1770908 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 1401684 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5265. Min Act: -0.1700
Data Index: 6372696 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5265. Min Act: -0.1700
Data Index: 198143 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5265. Min Act: -0.1700
Data Index: 2469441 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.4952. Min Act: -0.1700
Data Index: 1736117 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.4952. Min Act: -0.1700
Data Index: 3925944 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.4952. Min Act: -0.1700
Data Index: 766168 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19