Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2540 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8078. Min Range: -9.8078
Max Act: 9.8078. Min Act: -0.1700
Data Index: 5958436 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.7453. Min Act: -0.1700
Data Index: 8141964 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.7453. Min Act: -0.1700
Data Index: 1896332 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.6828. Min Act: -0.1700
Data Index: 5684605 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.6203. Min Act: -0.1700
Data Index: 2631189 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.6203. Min Act: -0.1700
Data Index: 1537343 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.5578. Min Act: -0.1700
Data Index: 7028597 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.5578. Min Act: -0.1700
Data Index: 7704398 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.5578. Min Act: -0.1700
Data Index: 627862 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.4953. Min Act: -0.1700
Data Index: 813442 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.4953. Min Act: -0.1700
Data Index: 4580228 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.4953. Min Act: -0.1700
Data Index: 4895052 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.4328. Min Act: -0.1700
Data Index: 6049255 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.4328. Min Act: -0.1700
Data Index: 4612725 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.3703. Min Act: -0.1700
Data Index: 3657241 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.4328. Min Act: -0.1700
Data Index: 4076016 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.3703. Min Act: -0.1700
Data Index: 4442080 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.3703. Min Act: -0.1700
Data Index: 633527 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.3703. Min Act: -0.1700
Data Index: 3786552 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8078. Min Range: -9.8078
Max Act: 8.3703. Min Act: -0.1700
Data Index: 427651 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19