Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 6985103 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.3197. Min Act: -0.1700
Data Index: 921049 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.2259. Min Act: -0.1700
Data Index: 802621 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.1634. Min Act: -0.1700
Data Index: 7256418 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.1009. Min Act: -0.1700
Data Index: 2395528 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.1009. Min Act: -0.1700
Data Index: 5570998 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.0697. Min Act: -0.1700
Data Index: 3325944 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.0384. Min Act: -0.1700
Data Index: 3972478 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.0384. Min Act: -0.1700
Data Index: 8253702 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.0384. Min Act: -0.1700
Data Index: 5079652 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.0384. Min Act: -0.1700
Data Index: 8012235 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7572. Min Range: -5.7572
Max Act: 4.9759. Min Act: -0.1700
Data Index: 6654603 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.0072. Min Act: -0.1700
Data Index: 8242775 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.0072. Min Act: -0.1700
Data Index: 5690834 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7572. Min Range: -5.7572
Max Act: 4.9447. Min Act: -0.1700
Data Index: 7308880 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7572. Min Range: -5.7572
Max Act: 4.9447. Min Act: -0.1700
Data Index: 8363495 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7572. Min Range: -5.7572
Max Act: 4.9447. Min Act: -0.1700
Data Index: 7819740 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7572. Min Range: -5.7572
Max Act: 4.9134. Min Act: -0.1700
Data Index: 7634220 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7572. Min Range: -5.7572
Max Act: 4.9134. Min Act: -0.1700
Data Index: 7291528 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7572. Min Range: -5.7572
Max Act: 4.9134. Min Act: -0.1700
Data Index: 3672322 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19