Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.5428. Min Act: -0.1700
Data Index: 630786 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.5428. Min Act: -0.1700
Data Index: 8814305 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.4803. Min Act: -0.1700
Data Index: 5845072 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.2928. Min Act: -0.1700
Data Index: 685597 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.2303. Min Act: -0.1700
Data Index: 5376742 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.1678. Min Act: -0.1700
Data Index: 844391 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.1053. Min Act: -0.1700
Data Index: 2816085 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.1053. Min Act: -0.1700
Data Index: 5376741 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.1678. Min Act: -0.1700
Data Index: 2603970 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.1053. Min Act: -0.1700
Data Index: 4764970 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.0428. Min Act: -0.1700
Data Index: 5376743 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.0428. Min Act: -0.1700
Data Index: 125008 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.0428. Min Act: -0.1700
Data Index: 2665446 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.0428. Min Act: -0.1700
Data Index: 6281197 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.0116. Min Act: -0.1700
Data Index: 778754 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5428. Min Range: -8.5428
Max Act: 8.0116. Min Act: -0.1700
Data Index: 56372 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5428. Min Range: -8.5428
Max Act: 7.9803. Min Act: -0.1700
Data Index: 3047374 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5428. Min Range: -8.5428
Max Act: 7.9178. Min Act: -0.1700
Data Index: 3274275 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5428. Min Range: -8.5428
Max Act: 7.9491. Min Act: -0.1700
Data Index: 812593 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5428. Min Range: -8.5428
Max Act: 7.9491. Min Act: -0.1700
Data Index: 6921081 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19