Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1256 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1200. Min Range: -6.1200
Max Act: 6.1200. Min Act: -0.1700
Data Index: 267256 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.9950. Min Act: -0.1700
Data Index: 8439428 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.9638. Min Act: -0.1700
Data Index: 7179290 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.9325. Min Act: -0.1700
Data Index: 8799774 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.9638. Min Act: -0.1700
Data Index: 7988580 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.9013. Min Act: -0.1700
Data Index: 2167404 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.8700. Min Act: -0.1700
Data Index: 6429364 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.8388. Min Act: -0.1700
Data Index: 6371292 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.7763. Min Act: -0.1700
Data Index: 4258128 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.7763. Min Act: -0.1700
Data Index: 7681198 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.7138. Min Act: -0.1700
Data Index: 7086985 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.7450. Min Act: -0.1700
Data Index: 7420040 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.7450. Min Act: -0.1700
Data Index: 7340581 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.7138. Min Act: -0.1700
Data Index: 873629 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.6513. Min Act: -0.1700
Data Index: 4179474 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.6513. Min Act: -0.1700
Data Index: 6460467 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.6200. Min Act: -0.1700
Data Index: 1758313 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.6200. Min Act: -0.1700
Data Index: 2687858 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.6200. Min Act: -0.1700
Data Index: 4164733 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1200. Min Range: -6.1200
Max Act: 5.6200. Min Act: -0.1700
Data Index: 7560401 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19