Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2312 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.8628. Min Act: -0.1700
Data Index: 6999089 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.8003. Min Act: -0.1700
Data Index: 6261330 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.7378. Min Act: -0.1700
Data Index: 5038235 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.6128. Min Act: -0.1700
Data Index: 7633462 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.4878. Min Act: -0.1700
Data Index: 406129 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.3628. Min Act: -0.1700
Data Index: 3720236 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.3003. Min Act: -0.1700
Data Index: 8067139 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.2378. Min Act: -0.1700
Data Index: 3142231 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.2378. Min Act: -0.1700
Data Index: 7630615 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 5437278 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 815157 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 7758094 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 8449778 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 1019605 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 2488276 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 675354 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 5865880 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1753. Min Act: -0.1700
Data Index: 4165188 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1128. Min Act: -0.1700
Data Index: 1659381 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8628. Min Range: -8.8628
Max Act: 8.1128. Min Act: -0.1700
Data Index: 4073350 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19