Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6503. Min Range: -9.6503
Max Act: 9.6503. Min Act: -0.1700
Data Index: 4419614 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6503. Min Range: -9.6503
Max Act: 9.5878. Min Act: -0.1700
Data Index: 8796032 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6503. Min Range: -9.6503
Max Act: 9.3378. Min Act: -0.1700
Data Index: 4825830 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6503. Min Range: -9.6503
Max Act: 9.3378. Min Act: -0.1700
Data Index: 3313653 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6503. Min Range: -9.6503
Max Act: 9.0878. Min Act: -0.1700
Data Index: 5996665 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.7753. Min Act: -0.1700
Data Index: 800271 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.7753. Min Act: -0.1700
Data Index: 3507570 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.7753. Min Act: -0.1700
Data Index: 7662322 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.7128. Min Act: -0.1700
Data Index: 2000968 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.7128. Min Act: -0.1700
Data Index: 5308300 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.6503. Min Act: -0.1700
Data Index: 7105858 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.5878. Min Act: -0.1700
Data Index: 8583822 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.5253. Min Act: -0.1700
Data Index: 6500965 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.5253. Min Act: -0.1700
Data Index: 4297963 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.4628. Min Act: -0.1700
Data Index: 7238385 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.4003. Min Act: -0.1700
Data Index: 2088006 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.4628. Min Act: -0.1700
Data Index: 978066 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.4628. Min Act: -0.1700
Data Index: 5874163 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.4628. Min Act: -0.1700
Data Index: 2766366 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6503. Min Range: -9.6503
Max Act: 8.4003. Min Act: -0.1700
Data Index: 976917 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19