Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3503. Min Range: -8.3503
Max Act: 8.3503. Min Act: -0.1700
Data Index: 4049239 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3503. Min Range: -8.3503
Max Act: 8.2878. Min Act: -0.1700
Data Index: 2997505 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.9753. Min Act: -0.1700
Data Index: 4933643 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.9128. Min Act: -0.1700
Data Index: 3073212 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.7878. Min Act: -0.1700
Data Index: 1245764 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.7253. Min Act: -0.1700
Data Index: 5582053 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.7253. Min Act: -0.1700
Data Index: 5002318 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.7253. Min Act: -0.1700
Data Index: 6673076 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.6628. Min Act: -0.1700
Data Index: 5420410 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.6003. Min Act: -0.1700
Data Index: 1173401 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.6003. Min Act: -0.1700
Data Index: 957523 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.6003. Min Act: -0.1700
Data Index: 8444278 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.6003. Min Act: -0.1700
Data Index: 981363 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.6003. Min Act: -0.1700
Data Index: 8591612 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.4753. Min Act: -0.1700
Data Index: 924236 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.5378. Min Act: -0.1700
Data Index: 951786 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.5378. Min Act: -0.1700
Data Index: 1005447 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.4753. Min Act: -0.1700
Data Index: 7690271 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.4753. Min Act: -0.1700
Data Index: 3506359 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3503. Min Range: -8.3503
Max Act: 7.4753. Min Act: -0.1700
Data Index: 2082597 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19