Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3288 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.7628. Min Act: -0.1700
Data Index: 8119718 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.7003. Min Act: -0.1700
Data Index: 5896349 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.7003. Min Act: -0.1700
Data Index: 8279013 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.5753. Min Act: -0.1700
Data Index: 5920881 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.5128. Min Act: -0.1700
Data Index: 2003357 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.5128. Min Act: -0.1700
Data Index: 7148716 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.5128. Min Act: -0.1700
Data Index: 448328 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.5128. Min Act: -0.1700
Data Index: 2747683 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.4503. Min Act: -0.1700
Data Index: 8826444 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.4190. Min Act: -0.1700
Data Index: 8145506 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.3565. Min Act: -0.1700
Data Index: 6830955 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.3253. Min Act: -0.1700
Data Index: 1196152 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.2940. Min Act: -0.1700
Data Index: 7496174 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.2940. Min Act: -0.1700
Data Index: 406801 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.2315. Min Act: -0.1700
Data Index: 6835662 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.2315. Min Act: -0.1700
Data Index: 4050670 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.2003. Min Act: -0.1700
Data Index: 4952393 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.2003. Min Act: -0.1700
Data Index: 6667628 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.1690. Min Act: -0.1700
Data Index: 6050624 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7628. Min Range: -7.7628
Max Act: 7.1690. Min Act: -0.1700
Data Index: 2709309 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19