Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3039. Min Range: -5.3039
Max Act: 5.3039. Min Act: -0.1700
Data Index: 1482246 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3039. Min Range: -5.3039
Max Act: 5.1789. Min Act: -0.1700
Data Index: 6243686 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3039. Min Range: -5.3039
Max Act: 5.0226. Min Act: -0.1700
Data Index: 2902761 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.9914. Min Act: -0.1700
Data Index: 2980592 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.9914. Min Act: -0.1700
Data Index: 7261806 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.9914. Min Act: -0.1700
Data Index: 5447513 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.9601. Min Act: -0.1700
Data Index: 496571 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.9601. Min Act: -0.1700
Data Index: 2248270 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.9289. Min Act: -0.1700
Data Index: 1919548 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.9289. Min Act: -0.1700
Data Index: 1140740 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8976. Min Act: -0.1700
Data Index: 2289252 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8664. Min Act: -0.1700
Data Index: 6830487 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8664. Min Act: -0.1700
Data Index: 8829743 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8664. Min Act: -0.1700
Data Index: 4604526 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8664. Min Act: -0.1700
Data Index: 6814317 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8351. Min Act: -0.1700
Data Index: 231916 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8351. Min Act: -0.1700
Data Index: 2606739 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8351. Min Act: -0.1700
Data Index: 784287 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8039. Min Act: -0.1700
Data Index: 1548718 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3039. Min Range: -5.3039
Max Act: 4.8039. Min Act: -0.1700
Data Index: 322367 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19