Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.7801. Min Act: -0.1700
Data Index: 6675208 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.7176. Min Act: -0.1700
Data Index: 6170022 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.7176. Min Act: -0.1700
Data Index: 4043649 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.5613. Min Act: -0.1700
Data Index: 5055555 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.5613. Min Act: -0.1700
Data Index: 7673697 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.3738. Min Act: -0.1700
Data Index: 6355332 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.3426. Min Act: -0.1700
Data Index: 1874387 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2801. Min Act: -0.1700
Data Index: 1468235 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2801. Min Act: -0.1700
Data Index: 5345069 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2801. Min Act: -0.1700
Data Index: 7690702 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2801. Min Act: -0.1700
Data Index: 2154117 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2488. Min Act: -0.1700
Data Index: 6085702 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2488. Min Act: -0.1700
Data Index: 6236191 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2488. Min Act: -0.1700
Data Index: 8577359 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2176. Min Act: -0.1700
Data Index: 1907745 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.2176. Min Act: -0.1700
Data Index: 2129564 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.1863. Min Act: -0.1700
Data Index: 5546709 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.1551. Min Act: -0.1700
Data Index: 2223673 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.1551. Min Act: -0.1700
Data Index: 7848874 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7801. Min Range: -6.7801
Max Act: 6.1863. Min Act: -0.1700
Data Index: 5905959 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19