Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5631 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.4151. Min Act: -0.1700
Data Index: 2051459 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.4151. Min Act: -0.1700
Data Index: 2998997 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.4151. Min Act: -0.1700
Data Index: 6033365 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.3838. Min Act: -0.1700
Data Index: 2460530 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.3526. Min Act: -0.1700
Data Index: 5117548 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.1963. Min Act: -0.1700
Data Index: 3571590 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.1651. Min Act: -0.1700
Data Index: 8733013 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.1338. Min Act: -0.1700
Data Index: 6050903 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.1026. Min Act: -0.1700
Data Index: 2539189 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.0713. Min Act: -0.1700
Data Index: 1262102 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4151. Min Range: -7.4151
Max Act: 7.0401. Min Act: -0.1700
Data Index: 2629596 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.9776. Min Act: -0.1700
Data Index: 823171 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.8838. Min Act: -0.1700
Data Index: 6735001 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.7588. Min Act: -0.1700
Data Index: 6391372 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.7901. Min Act: -0.1700
Data Index: 2089231 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.7901. Min Act: -0.1700
Data Index: 1180708 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.6963. Min Act: -0.1700
Data Index: 4687183 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.7276. Min Act: -0.1700
Data Index: 192420 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.7276. Min Act: -0.1700
Data Index: 6365731 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4151. Min Range: -7.4151
Max Act: 6.6963. Min Act: -0.1700
Data Index: 5361682 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19