Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1311 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.6241. Min Act: -0.1700
Data Index: 1846192 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.5616. Min Act: -0.1700
Data Index: 5896325 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.4991. Min Act: -0.1700
Data Index: 1631217 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.3741. Min Act: -0.1700
Data Index: 584643 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.3116. Min Act: -0.1700
Data Index: 5141101 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.3116. Min Act: -0.1700
Data Index: 2401863 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.1866. Min Act: -0.1700
Data Index: 3663134 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.0929. Min Act: -0.1700
Data Index: 8392240 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.0616. Min Act: -0.1700
Data Index: 4926257 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.0616. Min Act: -0.1700
Data Index: 3156514 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.0616. Min Act: -0.1700
Data Index: 6670657 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.0616. Min Act: -0.1700
Data Index: 4736501 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6241. Min Range: -8.6241
Max Act: 8.0616. Min Act: -0.1700
Data Index: 4578880 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6241. Min Range: -8.6241
Max Act: 7.9991. Min Act: -0.1700
Data Index: 5518025 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6241. Min Range: -8.6241
Max Act: 7.9991. Min Act: -0.1700
Data Index: 5855878 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6241. Min Range: -8.6241
Max Act: 7.9991. Min Act: -0.1700
Data Index: 7698135 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6241. Min Range: -8.6241
Max Act: 7.9679. Min Act: -0.1700
Data Index: 7993704 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6241. Min Range: -8.6241
Max Act: 7.9366. Min Act: -0.1700
Data Index: 1944541 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6241. Min Range: -8.6241
Max Act: 7.9054. Min Act: -0.1700
Data Index: 3365718 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6241. Min Range: -8.6241
Max Act: 7.9366. Min Act: -0.1700
Data Index: 4146865 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19