Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.6889. Min Act: -0.1700
Data Index: 1309662 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.5326. Min Act: -0.1700
Data Index: 1271170 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.5014. Min Act: -0.1700
Data Index: 7268951 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.4701. Min Act: -0.1700
Data Index: 2911754 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.4076. Min Act: -0.1700
Data Index: 2963861 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.4076. Min Act: -0.1700
Data Index: 1056884 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.3451. Min Act: -0.1700
Data Index: 6543871 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.3139. Min Act: -0.1700
Data Index: 2618267 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.2514. Min Act: -0.1700
Data Index: 3895536 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.2826. Min Act: -0.1700
Data Index: 4353643 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.2514. Min Act: -0.1700
Data Index: 532325 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.2201. Min Act: -0.1700
Data Index: 4299574 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.1889. Min Act: -0.1700
Data Index: 4540136 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.1889. Min Act: -0.1700
Data Index: 7032861 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.1889. Min Act: -0.1700
Data Index: 5727133 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.1889. Min Act: -0.1700
Data Index: 5319627 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.1889. Min Act: -0.1700
Data Index: 2774322 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.1889. Min Act: -0.1700
Data Index: 654814 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.1576. Min Act: -0.1700
Data Index: 880251 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6889. Min Range: -5.6889
Max Act: 5.1576. Min Act: -0.1700
Data Index: 2831763 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19