Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1606 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.2513. Min Act: -0.1700
Data Index: 6588892 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.2513. Min Act: -0.1700
Data Index: 5201446 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.2513. Min Act: -0.1700
Data Index: 89276 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.2513. Min Act: -0.1700
Data Index: 630851 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1888. Min Act: -0.1700
Data Index: 3374942 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1888. Min Act: -0.1700
Data Index: 8437860 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1888. Min Act: -0.1700
Data Index: 6114078 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1263. Min Act: -0.1700
Data Index: 6588900 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1263. Min Act: -0.1700
Data Index: 6588902 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1263. Min Act: -0.1700
Data Index: 1348493 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1263. Min Act: -0.1700
Data Index: 8134093 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1263. Min Act: -0.1700
Data Index: 481034 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1263. Min Act: -0.1700
Data Index: 8497084 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.0638. Min Act: -0.1700
Data Index: 6444104 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.1263. Min Act: -0.1700
Data Index: 481035 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.0013. Min Act: -0.1700
Data Index: 4102935 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.0013. Min Act: -0.1700
Data Index: 6588894 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.0013. Min Act: -0.1700
Data Index: 4643798 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.0638. Min Act: -0.1700
Data Index: 6588895 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2513. Min Range: -10.2513
Max Act: 10.0013. Min Act: -0.1700
Data Index: 6588898 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19