Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5867 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.4643. Min Act: -0.1700
Data Index: 3534968 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.3705. Min Act: -0.1700
Data Index: 5968502 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.2143. Min Act: -0.1700
Data Index: 3493616 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.0893. Min Act: -0.1700
Data Index: 8701824 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.1205. Min Act: -0.1700
Data Index: 4886055 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.0580. Min Act: -0.1700
Data Index: 5746197 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.0580. Min Act: -0.1700
Data Index: 1211555 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.0580. Min Act: -0.1700
Data Index: 2927882 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9955. Min Act: -0.1700
Data Index: 5031137 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9955. Min Act: -0.1700
Data Index: 3576744 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9955. Min Act: -0.1700
Data Index: 7900879 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4643. Min Range: -6.4643
Max Act: 6.0268. Min Act: -0.1700
Data Index: 6097924 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9643. Min Act: -0.1700
Data Index: 3956086 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9643. Min Act: -0.1700
Data Index: 5938879 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9330. Min Act: -0.1700
Data Index: 1966137 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9330. Min Act: -0.1700
Data Index: 4449874 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9330. Min Act: -0.1700
Data Index: 3478909 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9018. Min Act: -0.1700
Data Index: 61526 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9018. Min Act: -0.1700
Data Index: 3012297 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4643. Min Range: -6.4643
Max Act: 5.9018. Min Act: -0.1700
Data Index: 191077 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19