Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1328. Min Range: -8.1328
Max Act: 8.1328. Min Act: -0.1700
Data Index: 4860467 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1328. Min Range: -8.1328
Max Act: 8.0703. Min Act: -0.1700
Data Index: 5162908 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.9141. Min Act: -0.1700
Data Index: 3264477 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.8203. Min Act: -0.1700
Data Index: 311584 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.7891. Min Act: -0.1700
Data Index: 8688039 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.6328. Min Act: -0.1700
Data Index: 942892 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.6016. Min Act: -0.1700
Data Index: 6162293 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.5391. Min Act: -0.1700
Data Index: 1736094 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.4766. Min Act: -0.1700
Data Index: 4745892 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.4453. Min Act: -0.1700
Data Index: 3162494 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.4141. Min Act: -0.1700
Data Index: 2725325 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.3828. Min Act: -0.1700
Data Index: 1485724 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.4141. Min Act: -0.1700
Data Index: 7895376 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.3203. Min Act: -0.1700
Data Index: 3882531 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.3516. Min Act: -0.1700
Data Index: 2829934 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.3516. Min Act: -0.1700
Data Index: 3988783 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.3203. Min Act: -0.1700
Data Index: 2578589 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.2891. Min Act: -0.1700
Data Index: 8077815 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.3203. Min Act: -0.1700
Data Index: 2725324 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1328. Min Range: -8.1328
Max Act: 7.3203. Min Act: -0.1700
Data Index: 4293810 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19