Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2511 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.6492. Min Act: -0.1700
Data Index: 1115578 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.6492. Min Act: -0.1700
Data Index: 8642065 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.5867. Min Act: -0.1700
Data Index: 6221785 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.5867. Min Act: -0.1700
Data Index: 1596634 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.5867. Min Act: -0.1700
Data Index: 3633550 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.5867. Min Act: -0.1700
Data Index: 3633552 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.4617. Min Act: -0.1700
Data Index: 4799661 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.3992. Min Act: -0.1700
Data Index: 5050225 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.3992. Min Act: -0.1700
Data Index: 3633555 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.3367. Min Act: -0.1700
Data Index: 2249832 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.3367. Min Act: -0.1700
Data Index: 6728335 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.2117. Min Act: -0.1700
Data Index: 2568971 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.2117. Min Act: -0.1700
Data Index: 6336681 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.2117. Min Act: -0.1700
Data Index: 1115576 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.1492. Min Act: -0.1700
Data Index: 3101160 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.0867. Min Act: -0.1700
Data Index: 5924892 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.0867. Min Act: -0.1700
Data Index: 306567 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6492. Min Range: -8.6492
Max Act: 8.0242. Min Act: -0.1700
Data Index: 7538388 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6492. Min Range: -8.6492
Max Act: 7.9617. Min Act: -0.1700
Data Index: 3644847 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6492. Min Range: -8.6492
Max Act: 7.9617. Min Act: -0.1700
Data Index: 6136239 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19