Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.3832. Min Act: -0.1700
Data Index: 671486 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.3207. Min Act: -0.1700
Data Index: 5708918 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.2894. Min Act: -0.1700
Data Index: 5316935 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.2894. Min Act: -0.1700
Data Index: 28165 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.2582. Min Act: -0.1700
Data Index: 7613362 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1957. Min Act: -0.1700
Data Index: 1368768 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.2269. Min Act: -0.1700
Data Index: 8608462 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.2269. Min Act: -0.1700
Data Index: 7171580 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1957. Min Act: -0.1700
Data Index: 4451160 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.2269. Min Act: -0.1700
Data Index: 8001074 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1644. Min Act: -0.1700
Data Index: 440773 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1644. Min Act: -0.1700
Data Index: 1924035 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1644. Min Act: -0.1700
Data Index: 596851 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1644. Min Act: -0.1700
Data Index: 6656795 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1332. Min Act: -0.1700
Data Index: 3768901 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1332. Min Act: -0.1700
Data Index: 4031865 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1332. Min Act: -0.1700
Data Index: 8057612 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1644. Min Act: -0.1700
Data Index: 8479633 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1332. Min Act: -0.1700
Data Index: 3170621 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3832. Min Range: -4.3832
Max Act: 4.1332. Min Act: -0.1700
Data Index: 2221096 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19