Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5716. Min Range: -9.5716
Max Act: 9.5716. Min Act: -0.1700
Data Index: 8782905 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5716. Min Range: -9.5716
Max Act: 9.3216. Min Act: -0.1700
Data Index: 5008016 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5716. Min Range: -9.5716
Max Act: 9.0716. Min Act: -0.1700
Data Index: 2897508 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5716. Min Range: -9.5716
Max Act: 9.0716. Min Act: -0.1700
Data Index: 3236126 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.9466. Min Act: -0.1700
Data Index: 3484945 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.8841. Min Act: -0.1700
Data Index: 6586679 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.8841. Min Act: -0.1700
Data Index: 2051215 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.8216. Min Act: -0.1700
Data Index: 7643780 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.8216. Min Act: -0.1700
Data Index: 1472400 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.8216. Min Act: -0.1700
Data Index: 5284343 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.8216. Min Act: -0.1700
Data Index: 5185902 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.7591. Min Act: -0.1700
Data Index: 6688036 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.7591. Min Act: -0.1700
Data Index: 8222369 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.7591. Min Act: -0.1700
Data Index: 3342760 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.6341. Min Act: -0.1700
Data Index: 3034270 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.6966. Min Act: -0.1700
Data Index: 6145954 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.6966. Min Act: -0.1700
Data Index: 2496897 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.6966. Min Act: -0.1700
Data Index: 6156394 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.6341. Min Act: -0.1700
Data Index: 2962735 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5716. Min Range: -9.5716
Max Act: 8.6341. Min Act: -0.1700
Data Index: 7415718 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19