Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0492. Min Range: -8.0492
Max Act: 8.0492. Min Act: -0.1700
Data Index: 7913959 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0492. Min Range: -8.0492
Max Act: 8.0492. Min Act: -0.1700
Data Index: 8612153 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0492. Min Range: -8.0492
Max Act: 8.0492. Min Act: -0.1700
Data Index: 2807813 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.9242. Min Act: -0.1700
Data Index: 5131118 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 2361294 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7992. Min Act: -0.1700
Data Index: 8059628 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7367. Min Act: -0.1700
Data Index: 3825445 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7367. Min Act: -0.1700
Data Index: 5800981 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7367. Min Act: -0.1700
Data Index: 7960497 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7367. Min Act: -0.1700
Data Index: 7317126 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7367. Min Act: -0.1700
Data Index: 5987837 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.6742. Min Act: -0.1700
Data Index: 89042 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7367. Min Act: -0.1700
Data Index: 2184538 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7367. Min Act: -0.1700
Data Index: 3734527 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.6742. Min Act: -0.1700
Data Index: 5818256 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.6742. Min Act: -0.1700
Data Index: 7143788 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.6742. Min Act: -0.1700
Data Index: 4962532 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.6742. Min Act: -0.1700
Data Index: 4884210 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.6742. Min Act: -0.1700
Data Index: 40937 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.6742. Min Act: -0.1700
Data Index: 5694606 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19