Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 276 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5076. Min Range: -8.5076
Max Act: 8.5076. Min Act: -0.1700
Data Index: 2121730 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5076. Min Range: -8.5076
Max Act: 8.0076. Min Act: -0.1700
Data Index: 7244667 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.9451. Min Act: -0.1700
Data Index: 705594 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.8201. Min Act: -0.1700
Data Index: 4613353 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.7889. Min Act: -0.1700
Data Index: 8697359 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.6951. Min Act: -0.1700
Data Index: 6603796 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.6326. Min Act: -0.1700
Data Index: 5426568 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.6014. Min Act: -0.1700
Data Index: 3815965 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.5701. Min Act: -0.1700
Data Index: 6483559 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.5389. Min Act: -0.1700
Data Index: 5686197 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.4764. Min Act: -0.1700
Data Index: 3091577 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.4451. Min Act: -0.1700
Data Index: 3484928 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.4451. Min Act: -0.1700
Data Index: 8405452 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.4451. Min Act: -0.1700
Data Index: 3179484 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.3826. Min Act: -0.1700
Data Index: 7645177 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.3514. Min Act: -0.1700
Data Index: 1507632 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.3514. Min Act: -0.1700
Data Index: 2923245 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.3514. Min Act: -0.1700
Data Index: 2689847 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.2889. Min Act: -0.1700
Data Index: 7308192 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5076. Min Range: -8.5076
Max Act: 7.3201. Min Act: -0.1700
Data Index: 4140366 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19