Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.2951. Min Act: -0.1700
Data Index: 6086079 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.1388. Min Act: -0.1700
Data Index: 8633057 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 819722 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.8576. Min Act: -0.1700
Data Index: 3007721 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.8263. Min Act: -0.1700
Data Index: 6877620 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.8263. Min Act: -0.1700
Data Index: 3465100 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.7951. Min Act: -0.1700
Data Index: 1649065 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.7638. Min Act: -0.1700
Data Index: 8713041 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.7638. Min Act: -0.1700
Data Index: 3020394 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.6701. Min Act: -0.1700
Data Index: 6439244 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.7013. Min Act: -0.1700
Data Index: 2726485 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.7013. Min Act: -0.1700
Data Index: 975777 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.7013. Min Act: -0.1700
Data Index: 6330201 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.7013. Min Act: -0.1700
Data Index: 4396513 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.6701. Min Act: -0.1700
Data Index: 5508662 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.6701. Min Act: -0.1700
Data Index: 4453713 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.6388. Min Act: -0.1700
Data Index: 7841947 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.6388. Min Act: -0.1700
Data Index: 158098 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.6388. Min Act: -0.1700
Data Index: 2350838 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.6388. Min Act: -0.1700
Data Index: 2785750 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19