Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2032 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.2686. Min Act: -0.1700
Data Index: 6081699 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.1436. Min Act: -0.1700
Data Index: 4413760 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.0811. Min Act: -0.1700
Data Index: 443278 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.1124. Min Act: -0.1700
Data Index: 963139 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.0811. Min Act: -0.1700
Data Index: 1066173 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.0811. Min Act: -0.1700
Data Index: 4607856 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.0811. Min Act: -0.1700
Data Index: 7078787 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.0186. Min Act: -0.1700
Data Index: 2111275 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.0186. Min Act: -0.1700
Data Index: 1066171 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2686. Min Range: -4.2686
Max Act: 4.0498. Min Act: -0.1700
Data Index: 5687874 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9873. Min Act: -0.1700
Data Index: 4652394 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9873. Min Act: -0.1700
Data Index: 8233719 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9561. Min Act: -0.1700
Data Index: 6566916 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9561. Min Act: -0.1700
Data Index: 7306811 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9561. Min Act: -0.1700
Data Index: 3295667 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9248. Min Act: -0.1700
Data Index: 4732687 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9248. Min Act: -0.1700
Data Index: 4100777 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9248. Min Act: -0.1700
Data Index: 7484523 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.9248. Min Act: -0.1700
Data Index: 3074299 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2686. Min Range: -4.2686
Max Act: 3.8935. Min Act: -0.1700
Data Index: 4706513 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19