Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1078. Min Range: -5.1078
Max Act: 5.1078. Min Act: -0.1700
Data Index: 531584 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1078. Min Range: -5.1078
Max Act: 5.0141. Min Act: -0.1700
Data Index: 1981936 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.9828. Min Act: -0.1700
Data Index: 4813779 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.9516. Min Act: -0.1700
Data Index: 3638279 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.9516. Min Act: -0.1700
Data Index: 5694925 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.9828. Min Act: -0.1700
Data Index: 3785935 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.8891. Min Act: -0.1700
Data Index: 1532568 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.8578. Min Act: -0.1700
Data Index: 7947098 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.8578. Min Act: -0.1700
Data Index: 7925681 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.8891. Min Act: -0.1700
Data Index: 7562691 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.8266. Min Act: -0.1700
Data Index: 3785934 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.7641. Min Act: -0.1700
Data Index: 4190026 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.7641. Min Act: -0.1700
Data Index: 3372978 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.7328. Min Act: -0.1700
Data Index: 6858923 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.7328. Min Act: -0.1700
Data Index: 6106245 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.7016. Min Act: -0.1700
Data Index: 4574902 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.7328. Min Act: -0.1700
Data Index: 722849 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.6391. Min Act: -0.1700
Data Index: 1888567 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.6391. Min Act: -0.1700
Data Index: 1724887 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1078. Min Range: -5.1078
Max Act: 4.6391. Min Act: -0.1700
Data Index: 6300517 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19