Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.4491. Min Act: -0.1700
Data Index: 7685444 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.2616. Min Act: -0.1700
Data Index: 7834590 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.2303. Min Act: -0.1700
Data Index: 5577547 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.1678. Min Act: -0.1700
Data Index: 235400 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.1366. Min Act: -0.1700
Data Index: 6598882 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0741. Min Act: -0.1700
Data Index: 861110 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0741. Min Act: -0.1700
Data Index: 7366515 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0741. Min Act: -0.1700
Data Index: 5156027 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0741. Min Act: -0.1700
Data Index: 957869 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0428. Min Act: -0.1700
Data Index: 1586355 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0428. Min Act: -0.1700
Data Index: 3989293 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0428. Min Act: -0.1700
Data Index: 1417442 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0428. Min Act: -0.1700
Data Index: 4762806 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0116. Min Act: -0.1700
Data Index: 5352610 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0428. Min Act: -0.1700
Data Index: 7618052 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4491. Min Range: -5.4491
Max Act: 4.9803. Min Act: -0.1700
Data Index: 525486 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4491. Min Range: -5.4491
Max Act: 4.9803. Min Act: -0.1700
Data Index: 6535264 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4491. Min Range: -5.4491
Max Act: 4.9803. Min Act: -0.1700
Data Index: 2830119 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4491. Min Range: -5.4491
Max Act: 5.0116. Min Act: -0.1700
Data Index: 5432797 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4491. Min Range: -5.4491
Max Act: 4.9803. Min Act: -0.1700
Data Index: 6598883 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19