Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4013 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.8070. Min Act: -0.1700
Data Index: 2373981 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.8383. Min Act: -0.1700
Data Index: 1942757 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.7757. Min Act: -0.1700
Data Index: 1550709 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.7445. Min Act: -0.1700
Data Index: 3480568 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.7445. Min Act: -0.1700
Data Index: 728250 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.7757. Min Act: -0.1700
Data Index: 4957686 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.7132. Min Act: -0.1700
Data Index: 7667352 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.7445. Min Act: -0.1700
Data Index: 4905903 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.7132. Min Act: -0.1700
Data Index: 1000275 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.7132. Min Act: -0.1700
Data Index: 1157425 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6819. Min Act: -0.1700
Data Index: 1185491 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6819. Min Act: -0.1700
Data Index: 6234284 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6819. Min Act: -0.1700
Data Index: 3299131 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6506. Min Act: -0.1700
Data Index: 7645842 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6506. Min Act: -0.1700
Data Index: 895859 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6349. Min Act: -0.1700
Data Index: 8508932 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6506. Min Act: -0.1700
Data Index: 2171994 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6506. Min Act: -0.1700
Data Index: 6234282 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6506. Min Act: -0.1700
Data Index: 1591729 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8383. Min Range: -3.8383
Max Act: 3.6506. Min Act: -0.1700
Data Index: 7572312 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19