Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5946 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.4817. Min Act: -0.1700
Data Index: 4656374 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3879. Min Act: -0.1700
Data Index: 8099891 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2942. Min Act: -0.1700
Data Index: 6061838 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1692. Min Act: -0.1700
Data Index: 4810933 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1692. Min Act: -0.1700
Data Index: 5340438 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1067. Min Act: -0.1700
Data Index: 7021709 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1067. Min Act: -0.1700
Data Index: 3923357 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1379. Min Act: -0.1700
Data Index: 8329512 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 7779506 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 6303862 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0129. Min Act: -0.1700
Data Index: 5052076 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0129. Min Act: -0.1700
Data Index: 8547136 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 3852990 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0129. Min Act: -0.1700
Data Index: 3811446 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0129. Min Act: -0.1700
Data Index: 1593685 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4817. Min Range: -5.4817
Max Act: 4.9817. Min Act: -0.1700
Data Index: 4932551 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4817. Min Range: -5.4817
Max Act: 4.9817. Min Act: -0.1700
Data Index: 4944585 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4817. Min Range: -5.4817
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4903830 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4817. Min Range: -5.4817
Max Act: 4.9504. Min Act: -0.1700
Data Index: 6045008 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4817. Min Range: -5.4817
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4076465 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19