Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6405. Min Range: -8.6405
Max Act: 8.6405. Min Act: -0.1700
Data Index: 1453570 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6405. Min Range: -8.6405
Max Act: 8.6405. Min Act: -0.1700
Data Index: 6343387 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6405. Min Range: -8.6405
Max Act: 8.5780. Min Act: -0.1700
Data Index: 1394639 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6405. Min Range: -8.6405
Max Act: 8.5155. Min Act: -0.1700
Data Index: 5887097 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6405. Min Range: -8.6405
Max Act: 8.0780. Min Act: -0.1700
Data Index: 640622 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6405. Min Range: -8.6405
Max Act: 8.0155. Min Act: -0.1700
Data Index: 7847382 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6405. Min Range: -8.6405
Max Act: 8.0155. Min Act: -0.1700
Data Index: 7581743 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.9530. Min Act: -0.1700
Data Index: 8072850 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.8593. Min Act: -0.1700
Data Index: 4201497 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.8280. Min Act: -0.1700
Data Index: 2350991 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.7968. Min Act: -0.1700
Data Index: 2744897 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.7655. Min Act: -0.1700
Data Index: 4914255 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.7655. Min Act: -0.1700
Data Index: 3645894 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.7655. Min Act: -0.1700
Data Index: 4858159 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.7343. Min Act: -0.1700
Data Index: 4243747 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.7030. Min Act: -0.1700
Data Index: 8017168 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.6718. Min Act: -0.1700
Data Index: 5526410 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.6093. Min Act: -0.1700
Data Index: 2300698 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.6093. Min Act: -0.1700
Data Index: 4927620 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6405. Min Range: -8.6405
Max Act: 7.5468. Min Act: -0.1700
Data Index: 5418873 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19