Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1807. Min Range: -10.1807
Max Act: 10.1807. Min Act: -0.1700
Data Index: 5940346 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.9307. Min Act: -0.1700
Data Index: 2405738 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.8682. Min Act: -0.1700
Data Index: 4032103 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.8057. Min Act: -0.1700
Data Index: 7278265 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.8057. Min Act: -0.1700
Data Index: 2422556 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.7432. Min Act: -0.1700
Data Index: 6345731 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.6807. Min Act: -0.1700
Data Index: 5719047 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.6807. Min Act: -0.1700
Data Index: 4845456 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.6182. Min Act: -0.1700
Data Index: 6446050 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.5557. Min Act: -0.1700
Data Index: 63069 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.5557. Min Act: -0.1700
Data Index: 1181715 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.5557. Min Act: -0.1700
Data Index: 1652629 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.5557. Min Act: -0.1700
Data Index: 2009288 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.4932. Min Act: -0.1700
Data Index: 6703293 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.4932. Min Act: -0.1700
Data Index: 2541735 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.4932. Min Act: -0.1700
Data Index: 2325591 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.4932. Min Act: -0.1700
Data Index: 8627716 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.4307. Min Act: -0.1700
Data Index: 2903154 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.4307. Min Act: -0.1700
Data Index: 6311547 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1807. Min Range: -10.1807
Max Act: 9.4307. Min Act: -0.1700
Data Index: 3297874 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19