Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5893 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1036. Min Range: -7.1036
Max Act: 7.1036. Min Act: -0.1700
Data Index: 3066309 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1036. Min Range: -7.1036
Max Act: 7.0099. Min Act: -0.1700
Data Index: 6802673 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.9474. Min Act: -0.1700
Data Index: 7154556 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.8849. Min Act: -0.1700
Data Index: 2345858 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.8536. Min Act: -0.1700
Data Index: 1531539 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.8224. Min Act: -0.1700
Data Index: 5544168 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.8224. Min Act: -0.1700
Data Index: 5025736 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.8224. Min Act: -0.1700
Data Index: 63288 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.7599. Min Act: -0.1700
Data Index: 3851817 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.7599. Min Act: -0.1700
Data Index: 1869324 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6974. Min Act: -0.1700
Data Index: 4833095 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6974. Min Act: -0.1700
Data Index: 3212945 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6974. Min Act: -0.1700
Data Index: 1759668 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6661. Min Act: -0.1700
Data Index: 1981012 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6661. Min Act: -0.1700
Data Index: 8078890 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6349. Min Act: -0.1700
Data Index: 8633729 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6349. Min Act: -0.1700
Data Index: 6781029 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6661. Min Act: -0.1700
Data Index: 2262022 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6036. Min Act: -0.1700
Data Index: 5423628 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1036. Min Range: -7.1036
Max Act: 6.6036. Min Act: -0.1700
Data Index: 2685720 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19