Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 562 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2079. Min Range: -8.2079
Max Act: 8.1766. Min Act: -0.1700
Data Index: 6864913 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2079. Min Range: -8.2079
Max Act: 8.2079. Min Act: -0.1700
Data Index: 2297113 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2079. Min Range: -8.2079
Max Act: 8.1454. Min Act: -0.1700
Data Index: 5510332 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2079. Min Range: -8.2079
Max Act: 8.0516. Min Act: -0.1700
Data Index: 8690072 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.9891. Min Act: -0.1700
Data Index: 8673954 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.9579. Min Act: -0.1700
Data Index: 2534091 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.9266. Min Act: -0.1700
Data Index: 7639874 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.9266. Min Act: -0.1700
Data Index: 7676044 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.8641. Min Act: -0.1700
Data Index: 681655 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.8016. Min Act: -0.1700
Data Index: 78989 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.8329. Min Act: -0.1700
Data Index: 4232127 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.8329. Min Act: -0.1700
Data Index: 336983 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.7704. Min Act: -0.1700
Data Index: 537497 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.7391. Min Act: -0.1699
Data Index: 3374898 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.7079. Min Act: -0.1700
Data Index: 4186054 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.7079. Min Act: -0.1700
Data Index: 5485118 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.6766. Min Act: -0.1700
Data Index: 8154399 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.7079. Min Act: -0.1700
Data Index: 1559231 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.6766. Min Act: -0.1700
Data Index: 1458386 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2079. Min Range: -8.2079
Max Act: 7.6766. Min Act: -0.1700
Data Index: 3922450 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19