Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6029. Min Range: -9.6029
Max Act: 9.6029. Min Act: -0.1700
Data Index: 3308188 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6029. Min Range: -9.6029
Max Act: 9.3529. Min Act: -0.1700
Data Index: 3373807 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6029. Min Range: -9.6029
Max Act: 9.0404. Min Act: -0.1700
Data Index: 7340030 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6029. Min Range: -9.6029
Max Act: 9.0404. Min Act: -0.1700
Data Index: 2414435 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6029. Min Range: -9.6029
Max Act: 9.0404. Min Act: -0.1700
Data Index: 5168622 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.9154. Min Act: -0.1700
Data Index: 8730827 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.7279. Min Act: -0.1700
Data Index: 1144738 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.7279. Min Act: -0.1700
Data Index: 7164081 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.6029. Min Act: -0.1700
Data Index: 4031956 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.6029. Min Act: -0.1700
Data Index: 6119147 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.6029. Min Act: -0.1700
Data Index: 6435812 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.6029. Min Act: -0.1700
Data Index: 1552257 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.6029. Min Act: -0.1700
Data Index: 4195277 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.5404. Min Act: -0.1700
Data Index: 4264127 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.5404. Min Act: -0.1700
Data Index: 4226929 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.5404. Min Act: -0.1700
Data Index: 5237415 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.5404. Min Act: -0.1700
Data Index: 3631463 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.5404. Min Act: -0.1700
Data Index: 5380611 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.4779. Min Act: -0.1700
Data Index: 4305022 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6029. Min Range: -9.6029
Max Act: 8.4779. Min Act: -0.1700
Data Index: 127494 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19