Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.5129. Min Act: -0.1700
Data Index: 877182 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.3879. Min Act: -0.1700
Data Index: 804398 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.3567. Min Act: -0.1700
Data Index: 1162925 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.3567. Min Act: -0.1700
Data Index: 8260436 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.2942. Min Act: -0.1700
Data Index: 4232774 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.2317. Min Act: -0.1700
Data Index: 8342534 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.2317. Min Act: -0.1700
Data Index: 996203 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.2004. Min Act: -0.1700
Data Index: 8011694 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.2004. Min Act: -0.1700
Data Index: 133540 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.2004. Min Act: -0.1700
Data Index: 4296206 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1692. Min Act: -0.1700
Data Index: 918248 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1692. Min Act: -0.1700
Data Index: 4077486 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1379. Min Act: -0.1700
Data Index: 4756059 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1692. Min Act: -0.1700
Data Index: 7963762 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1379. Min Act: -0.1700
Data Index: 7808495 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1379. Min Act: -0.1700
Data Index: 6111734 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1379. Min Act: -0.1700
Data Index: 2744221 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1067. Min Act: -0.1700
Data Index: 6395494 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1067. Min Act: -0.1700
Data Index: 1003871 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5129. Min Range: -5.5129
Max Act: 5.1067. Min Act: -0.1700
Data Index: 2858498 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19