Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.6194. Min Act: -0.1700
Data Index: 5892434 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.5881. Min Act: -0.1700
Data Index: 6842903 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.5881. Min Act: -0.1700
Data Index: 1150928 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.5881. Min Act: -0.1700
Data Index: 3478982 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.5569. Min Act: -0.1700
Data Index: 632208 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.5256. Min Act: -0.1700
Data Index: 3940201 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.5256. Min Act: -0.1700
Data Index: 2586053 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.5256. Min Act: -0.1700
Data Index: 4281746 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.5256. Min Act: -0.1700
Data Index: 1779092 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4944. Min Act: -0.1700
Data Index: 5937100 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4944. Min Act: -0.1700
Data Index: 5147822 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4944. Min Act: -0.1700
Data Index: 3888906 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4631. Min Act: -0.1700
Data Index: 4441254 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4631. Min Act: -0.1700
Data Index: 2025065 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4631. Min Act: -0.1700
Data Index: 2728862 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4631. Min Act: -0.1700
Data Index: 8524971 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4631. Min Act: -0.1700
Data Index: 2786869 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4318. Min Act: -0.1700
Data Index: 1278911 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4318. Min Act: -0.1700
Data Index: 2288589 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6194. Min Range: -4.6194
Max Act: 4.4631. Min Act: -0.1700
Data Index: 7697576 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19