Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 378 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.4641. Min Act: -0.1700
Data Index: 1139206 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.4016. Min Act: -0.1700
Data Index: 3025208 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3703. Min Act: -0.1700
Data Index: 3099672 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3391. Min Act: -0.1700
Data Index: 6975852 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2766. Min Act: -0.1700
Data Index: 225300 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2141. Min Act: -0.1700
Data Index: 1727415 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2141. Min Act: -0.1700
Data Index: 8042151 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.1828. Min Act: -0.1700
Data Index: 4156143 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.1516. Min Act: -0.1700
Data Index: 2616355 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0891. Min Act: -0.1700
Data Index: 1060839 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.1203. Min Act: -0.1700
Data Index: 4511570 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.1203. Min Act: -0.1700
Data Index: 4204847 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0891. Min Act: -0.1700
Data Index: 3160426 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0891. Min Act: -0.1700
Data Index: 1891449 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0891. Min Act: -0.1700
Data Index: 6651856 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0578. Min Act: -0.1700
Data Index: 2490966 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9953. Min Act: -0.1700
Data Index: 5770754 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0266. Min Act: -0.1700
Data Index: 6500980 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0266. Min Act: -0.1700
Data Index: 1909778 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0266. Min Act: -0.1700
Data Index: 3321635 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19