Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1942 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.2237. Min Act: -0.1700
Data Index: 4350071 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.2237. Min Act: -0.1700
Data Index: 3846009 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.1612. Min Act: -0.1700
Data Index: 7481221 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.1612. Min Act: -0.1700
Data Index: 8489944 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.1612. Min Act: -0.1700
Data Index: 6409273 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.1612. Min Act: -0.1700
Data Index: 7369256 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.1612. Min Act: -0.1700
Data Index: 8758141 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.0987. Min Act: -0.1700
Data Index: 5726996 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.0362. Min Act: -0.1700
Data Index: 4932982 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.0987. Min Act: -0.1700
Data Index: 5249619 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2237. Min Range: -8.2237
Max Act: 8.0362. Min Act: -0.1700
Data Index: 7378651 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9737. Min Act: -0.1700
Data Index: 1377699 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9737. Min Act: -0.1700
Data Index: 4328758 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9112. Min Act: -0.1700
Data Index: 130154 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9737. Min Act: -0.1700
Data Index: 4929449 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9737. Min Act: -0.1700
Data Index: 606930 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9737. Min Act: -0.1700
Data Index: 4363049 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9112. Min Act: -0.1700
Data Index: 6854168 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9112. Min Act: -0.1700
Data Index: 5676542 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2237. Min Range: -8.2237
Max Act: 7.9112. Min Act: -0.1700
Data Index: 2004700 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19