Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2584 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.6422. Min Act: -0.1700
Data Index: 1335906 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.4859. Min Act: -0.1700
Data Index: 4776025 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.3922. Min Act: -0.1700
Data Index: 742837 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.3922. Min Act: -0.1700
Data Index: 2569554 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.3922. Min Act: -0.1700
Data Index: 2875469 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.3609. Min Act: -0.1700
Data Index: 4135121 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.3922. Min Act: -0.1700
Data Index: 2766349 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.3609. Min Act: -0.1700
Data Index: 7231671 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.3297. Min Act: -0.1700
Data Index: 3168510 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.3297. Min Act: -0.1700
Data Index: 2756090 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2984. Min Act: -0.1700
Data Index: 4935712 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2984. Min Act: -0.1700
Data Index: 5108996 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2984. Min Act: -0.1700
Data Index: 6318628 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2672. Min Act: -0.1700
Data Index: 8327535 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2672. Min Act: -0.1700
Data Index: 7575619 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2672. Min Act: -0.1700
Data Index: 7846416 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2359. Min Act: -0.1700
Data Index: 8326280 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2047. Min Act: -0.1700
Data Index: 7333849 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2047. Min Act: -0.1700
Data Index: 6075136 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6422. Min Range: -6.6422
Max Act: 6.2047. Min Act: -0.1700
Data Index: 65409 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19