Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.8037. Min Act: -0.1700
Data Index: 7935566 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.6919. Min Act: -0.1698
Data Index: 7744866 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.6759. Min Act: -0.1700
Data Index: 5740530 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.6599. Min Act: -0.1700
Data Index: 1499250 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.6438. Min Act: -0.1700
Data Index: 3392047 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.6278. Min Act: -0.1700
Data Index: 1499249 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.6278. Min Act: -0.1700
Data Index: 2606531 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.5795. Min Act: -0.1700
Data Index: 3222156 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.5472. Min Act: -0.1692
Data Index: 90716 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.5311. Min Act: -0.1691
Data Index: 3730731 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.5311. Min Act: -0.1678
Data Index: 4882045 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.5311. Min Act: -0.1700
Data Index: 5831537 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.5149. Min Act: -0.1696
Data Index: 3412026 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.5311. Min Act: -0.1699
Data Index: 8324043 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.4987. Min Act: -0.1694
Data Index: 39175 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.4987. Min Act: -0.1692
Data Index: 5641962 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.4825. Min Act: -0.1700
Data Index: 7327014 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.4825. Min Act: -0.1698
Data Index: 4284979 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.4987. Min Act: -0.1699
Data Index: 8658016 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8037. Min Range: -2.8037
Max Act: 2.4825. Min Act: -0.1698
Data Index: 3726819 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19