Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0669. Min Range: -10.0669
Max Act: 10.0669. Min Act: -0.1700
Data Index: 8581078 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0669. Min Range: -10.0669
Max Act: 9.7544. Min Act: -0.1700
Data Index: 1414383 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0669. Min Range: -10.0669
Max Act: 9.6919. Min Act: -0.1700
Data Index: 3880942 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0669. Min Range: -10.0669
Max Act: 9.5669. Min Act: -0.1700
Data Index: 8490699 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0669. Min Range: -10.0669
Max Act: 9.2544. Min Act: -0.1700
Data Index: 3367028 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0669. Min Range: -10.0669
Max Act: 9.1294. Min Act: -0.1700
Data Index: 3945765 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0669. Min Range: -10.0669
Max Act: 9.0669. Min Act: -0.1700
Data Index: 1274390 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0669. Min Range: -10.0669
Max Act: 9.0044. Min Act: -0.1700
Data Index: 1525761 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.9419. Min Act: -0.1700
Data Index: 5679230 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.8794. Min Act: -0.1700
Data Index: 2102235 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.9419. Min Act: -0.1700
Data Index: 3540761 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.8794. Min Act: -0.1700
Data Index: 826891 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.7544. Min Act: -0.1700
Data Index: 4399047 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.7544. Min Act: -0.1700
Data Index: 4954969 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.7544. Min Act: -0.1700
Data Index: 3875841 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.6919. Min Act: -0.1700
Data Index: 5789964 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.6294. Min Act: -0.1700
Data Index: 5283881 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.5669. Min Act: -0.1700
Data Index: 5788093 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.5669. Min Act: -0.1700
Data Index: 2224666 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0669. Min Range: -10.0669
Max Act: 8.5044. Min Act: -0.1700
Data Index: 419651 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19