Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1690. Min Range: -6.1690
Max Act: 6.1690. Min Act: -0.1700
Data Index: 4853058 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1690. Min Range: -6.1690
Max Act: 6.1065. Min Act: -0.1700
Data Index: 775585 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1690. Min Range: -6.1690
Max Act: 6.1377. Min Act: -0.1700
Data Index: 729346 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1690. Min Range: -6.1690
Max Act: 6.0752. Min Act: -0.1700
Data Index: 3833765 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1690. Min Range: -6.1690
Max Act: 6.0752. Min Act: -0.1700
Data Index: 729347 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1690. Min Range: -6.1690
Max Act: 6.0127. Min Act: -0.1700
Data Index: 8543271 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1690. Min Range: -6.1690
Max Act: 6.0127. Min Act: -0.1700
Data Index: 5879878 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.9815. Min Act: -0.1700
Data Index: 5015574 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.9815. Min Act: -0.1700
Data Index: 7617090 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.9502. Min Act: -0.1700
Data Index: 5254823 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.9190. Min Act: -0.1700
Data Index: 7332856 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.8565. Min Act: -0.1700
Data Index: 8596782 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.8565. Min Act: -0.1700
Data Index: 7969747 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.8565. Min Act: -0.1700
Data Index: 5474355 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.8565. Min Act: -0.1700
Data Index: 4102321 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.8565. Min Act: -0.1700
Data Index: 4793082 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.8565. Min Act: -0.1700
Data Index: 1227925 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.8252. Min Act: -0.1700
Data Index: 4111628 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.8565. Min Act: -0.1700
Data Index: 6752002 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1690. Min Range: -6.1690
Max Act: 5.7940. Min Act: -0.1700
Data Index: 6166267 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19