Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4208 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0324. Min Range: -5.0324
Max Act: 5.0324. Min Act: -0.1700
Data Index: 127563 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0324. Min Range: -5.0324
Max Act: 5.0011. Min Act: -0.1700
Data Index: 8352815 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.9699. Min Act: -0.1700
Data Index: 5369990 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.9074. Min Act: -0.1700
Data Index: 2324018 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.8136. Min Act: -0.1700
Data Index: 3730824 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.7824. Min Act: -0.1700
Data Index: 8112849 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.7511. Min Act: -0.1700
Data Index: 296314 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.7511. Min Act: -0.1700
Data Index: 7159534 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.6886. Min Act: -0.1700
Data Index: 2737002 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.6574. Min Act: -0.1700
Data Index: 30635 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.6261. Min Act: -0.1700
Data Index: 1119110 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.5949. Min Act: -0.1700
Data Index: 30642 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.5636. Min Act: -0.1700
Data Index: 2413010 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.5636. Min Act: -0.1700
Data Index: 4078261 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.5011. Min Act: -0.1700
Data Index: 2977771 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.5324. Min Act: -0.1700
Data Index: 3914390 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.5324. Min Act: -0.1700
Data Index: 4569189 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.4699. Min Act: -0.1700
Data Index: 6934643 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.5011. Min Act: -0.1700
Data Index: 1141778 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0324. Min Range: -5.0324
Max Act: 4.5011. Min Act: -0.1700
Data Index: 34257 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19