Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0493. Min Range: -5.0493
Max Act: 5.0493. Min Act: -0.1700
Data Index: 3765727 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.8930. Min Act: -0.1700
Data Index: 1757232 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.7993. Min Act: -0.1700
Data Index: 2932809 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.7368. Min Act: -0.1700
Data Index: 5424609 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.7368. Min Act: -0.1700
Data Index: 8311940 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.6743. Min Act: -0.1700
Data Index: 1060261 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.6430. Min Act: -0.1700
Data Index: 4874799 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.6430. Min Act: -0.1700
Data Index: 34537 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.6118. Min Act: -0.1700
Data Index: 2890882 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5805. Min Act: -0.1700
Data Index: 6180816 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5493. Min Act: -0.1700
Data Index: 6505077 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5805. Min Act: -0.1700
Data Index: 2189407 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5493. Min Act: -0.1700
Data Index: 4054934 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5805. Min Act: -0.1700
Data Index: 1086146 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5493. Min Act: -0.1700
Data Index: 8180413 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5180. Min Act: -0.1700
Data Index: 7648835 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5180. Min Act: -0.1700
Data Index: 2959171 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5180. Min Act: -0.1700
Data Index: 8139398 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5180. Min Act: -0.1700
Data Index: 7504949 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0493. Min Range: -5.0493
Max Act: 4.5180. Min Act: -0.1700
Data Index: 7973552 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19