Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1431 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.6889. Min Act: -0.1700
Data Index: 5495208 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.1889. Min Act: -0.1700
Data Index: 5504087 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.1576. Min Act: -0.1700
Data Index: 905650 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.1264. Min Act: -0.1700
Data Index: 3761772 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.0014. Min Act: -0.1700
Data Index: 4517272 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.9389. Min Act: -0.1700
Data Index: 3409396 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.9389. Min Act: -0.1700
Data Index: 1174269 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.9076. Min Act: -0.1700
Data Index: 3603747 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.8764. Min Act: -0.1700
Data Index: 3033584 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.8451. Min Act: -0.1700
Data Index: 7656147 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.8451. Min Act: -0.1700
Data Index: 6407374 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.7514. Min Act: -0.1700
Data Index: 8481910 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.7826. Min Act: -0.1700
Data Index: 1196976 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.7826. Min Act: -0.1700
Data Index: 2692199 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.7826. Min Act: -0.1700
Data Index: 266798 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.7826. Min Act: -0.1700
Data Index: 4892722 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.7514. Min Act: -0.1700
Data Index: 453938 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.7201. Min Act: -0.1700
Data Index: 7316859 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.6889. Min Act: -0.1700
Data Index: 7729497 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6889. Min Range: -7.6889
Max Act: 6.7201. Min Act: -0.1700
Data Index: 8604935 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19