Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0913. Min Range: -8.0913
Max Act: 8.0913. Min Act: -0.1700
Data Index: 8032480 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0913. Min Range: -8.0913
Max Act: 8.0288. Min Act: -0.1700
Data Index: 3643317 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.9038. Min Act: -0.1700
Data Index: 709748 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.7788. Min Act: -0.1700
Data Index: 7149346 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.7788. Min Act: -0.1700
Data Index: 2678165 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.7788. Min Act: -0.1700
Data Index: 7493505 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.7788. Min Act: -0.1700
Data Index: 6783293 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.6851. Min Act: -0.1700
Data Index: 3396516 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.6851. Min Act: -0.1700
Data Index: 1198951 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.6851. Min Act: -0.1700
Data Index: 3790617 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.6538. Min Act: -0.1700
Data Index: 6457308 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5601. Min Act: -0.1700
Data Index: 7952691 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5913. Min Act: -0.1700
Data Index: 2547523 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5601. Min Act: -0.1700
Data Index: 4340349 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5601. Min Act: -0.1700
Data Index: 5196251 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5601. Min Act: -0.1700
Data Index: 5396227 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5601. Min Act: -0.1700
Data Index: 8804034 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5601. Min Act: -0.1700
Data Index: 623447 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5288. Min Act: -0.1700
Data Index: 254225 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0913. Min Range: -8.0913
Max Act: 7.5288. Min Act: -0.1700
Data Index: 5381758 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19