Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4073 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.5705. Min Act: -0.1700
Data Index: 1300739 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.5080. Min Act: -0.1700
Data Index: 822209 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3830. Min Act: -0.1700
Data Index: 372876 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.4142. Min Act: -0.1700
Data Index: 3086361 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3205. Min Act: -0.1700
Data Index: 1956590 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3205. Min Act: -0.1700
Data Index: 1095170 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.2892. Min Act: -0.1700
Data Index: 7002846 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.2267. Min Act: -0.1700
Data Index: 5993988 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.2580. Min Act: -0.1700
Data Index: 6409348 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.2267. Min Act: -0.1700
Data Index: 3178024 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.2267. Min Act: -0.1700
Data Index: 7721496 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.2267. Min Act: -0.1700
Data Index: 4537348 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.1955. Min Act: -0.1700
Data Index: 6912644 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.1955. Min Act: -0.1700
Data Index: 5070989 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.1642. Min Act: -0.1700
Data Index: 6891963 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.1642. Min Act: -0.1700
Data Index: 1760923 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.1330. Min Act: -0.1700
Data Index: 771796 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.1642. Min Act: -0.1700
Data Index: 7566708 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.1330. Min Act: -0.1700
Data Index: 1711831 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.1330. Min Act: -0.1700
Data Index: 858603 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19