Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 338 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0377. Min Range: -10.0377
Max Act: 10.0377. Min Act: -0.1700
Data Index: 1868883 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.9127. Min Act: -0.1700
Data Index: 6316016 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.8502. Min Act: -0.1700
Data Index: 7703726 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.6002. Min Act: -0.1700
Data Index: 288261 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.5377. Min Act: -0.1700
Data Index: 8707824 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.4752. Min Act: -0.1700
Data Index: 4858260 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.4127. Min Act: -0.1700
Data Index: 6810798 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.4127. Min Act: -0.1700
Data Index: 5155277 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.4127. Min Act: -0.1700
Data Index: 6915081 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.3502. Min Act: -0.1700
Data Index: 4768767 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2877. Min Act: -0.1700
Data Index: 7675597 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2877. Min Act: -0.1700
Data Index: 7543996 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2877. Min Act: -0.1700
Data Index: 7584397 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2877. Min Act: -0.1700
Data Index: 5016053 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2252. Min Act: -0.1700
Data Index: 326963 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.1627. Min Act: -0.1700
Data Index: 6728595 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2252. Min Act: -0.1700
Data Index: 3711218 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2252. Min Act: -0.1700
Data Index: 133873 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2252. Min Act: -0.1700
Data Index: 6810799 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0377. Min Range: -10.0377
Max Act: 9.2252. Min Act: -0.1700
Data Index: 8258456 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19