Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6054. Min Range: -8.6054
Max Act: 8.6054. Min Act: -0.1700
Data Index: 7999841 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6054. Min Range: -8.6054
Max Act: 8.2929. Min Act: -0.1700
Data Index: 2252061 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6054. Min Range: -8.6054
Max Act: 8.2929. Min Act: -0.1700
Data Index: 4266353 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6054. Min Range: -8.6054
Max Act: 8.2929. Min Act: -0.1700
Data Index: 5943580 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6054. Min Range: -8.6054
Max Act: 8.1054. Min Act: -0.1700
Data Index: 6907729 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6054. Min Range: -8.6054
Max Act: 8.0429. Min Act: -0.1700
Data Index: 1563188 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9179. Min Act: -0.1700
Data Index: 8423621 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9804. Min Act: -0.1700
Data Index: 6027330 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9179. Min Act: -0.1700
Data Index: 3784842 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9179. Min Act: -0.1700
Data Index: 2079938 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9179. Min Act: -0.1700
Data Index: 6804870 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9179. Min Act: -0.1700
Data Index: 6077696 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9179. Min Act: -0.1700
Data Index: 588414 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9804. Min Act: -0.1700
Data Index: 304196 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.9179. Min Act: -0.1700
Data Index: 3411055 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.8554. Min Act: -0.1700
Data Index: 7706450 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.7929. Min Act: -0.1700
Data Index: 3960484 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.7929. Min Act: -0.1700
Data Index: 3217414 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.7929. Min Act: -0.1700
Data Index: 3788291 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6054. Min Range: -8.6054
Max Act: 7.7929. Min Act: -0.1700
Data Index: 5462400 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19