Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1911 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0317. Min Range: -7.0317
Max Act: 7.0317. Min Act: -0.1700
Data Index: 3477223 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.8442. Min Act: -0.1700
Data Index: 6810012 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.5004. Min Act: -0.1700
Data Index: 8239845 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3754. Min Act: -0.1700
Data Index: 8766768 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3129. Min Act: -0.1700
Data Index: 2272245 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2504. Min Act: -0.1700
Data Index: 6328132 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.1879. Min Act: -0.1700
Data Index: 1634798 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.0629. Min Act: -0.1700
Data Index: 458698 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.0317. Min Act: -0.1700
Data Index: 1252545 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.0317. Min Act: -0.1700
Data Index: 701519 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.0629. Min Act: -0.1700
Data Index: 8112254 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.0004. Min Act: -0.1700
Data Index: 4773149 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0317. Min Range: -7.0317
Max Act: 5.9692. Min Act: -0.1700
Data Index: 4293570 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0317. Min Range: -7.0317
Max Act: 5.9379. Min Act: -0.1700
Data Index: 3349904 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0317. Min Range: -7.0317
Max Act: 5.9379. Min Act: -0.1700
Data Index: 6796784 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0317. Min Range: -7.0317
Max Act: 5.9067. Min Act: -0.1700
Data Index: 2818161 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0317. Min Range: -7.0317
Max Act: 5.9067. Min Act: -0.1700
Data Index: 1121188 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0317. Min Range: -7.0317
Max Act: 5.9067. Min Act: -0.1700
Data Index: 7168777 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0317. Min Range: -7.0317
Max Act: 5.9067. Min Act: -0.1700
Data Index: 7121060 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0317. Min Range: -7.0317
Max Act: 5.8754. Min Act: -0.1700
Data Index: 3835813 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19