Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.8395. Min Act: -0.1700
Data Index: 7876583 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.7770. Min Act: -0.1700
Data Index: 6448121 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.8082. Min Act: -0.1700
Data Index: 5058204 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.7457. Min Act: -0.1700
Data Index: 6262003 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.7145. Min Act: -0.1700
Data Index: 5777580 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.7145. Min Act: -0.1700
Data Index: 4283373 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.7145. Min Act: -0.1700
Data Index: 3142060 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.7145. Min Act: -0.1700
Data Index: 6374137 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.7145. Min Act: -0.1700
Data Index: 3134939 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.6832. Min Act: -0.1700
Data Index: 5977436 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.6520. Min Act: -0.1700
Data Index: 1639160 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.6520. Min Act: -0.1700
Data Index: 8663517 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.6520. Min Act: -0.1700
Data Index: 8367275 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.6520. Min Act: -0.1700
Data Index: 6211233 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.6207. Min Act: -0.1700
Data Index: 7125485 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.5895. Min Act: -0.1700
Data Index: 6773308 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.5895. Min Act: -0.1700
Data Index: 4105983 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.5895. Min Act: -0.1700
Data Index: 1639159 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.5895. Min Act: -0.1700
Data Index: 33576 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8395. Min Range: -6.8395
Max Act: 6.5582. Min Act: -0.1700
Data Index: 5446584 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19