Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3485. Min Range: -6.3485
Max Act: 6.3485. Min Act: -0.1700
Data Index: 4406325 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3485. Min Range: -6.3485
Max Act: 6.0672. Min Act: -0.1700
Data Index: 943012 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3485. Min Range: -6.3485
Max Act: 6.0047. Min Act: -0.1700
Data Index: 5897546 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3485. Min Range: -6.3485
Max Act: 6.0047. Min Act: -0.1700
Data Index: 5207634 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.9422. Min Act: -0.1699
Data Index: 4072631 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.9110. Min Act: -0.1700
Data Index: 653743 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.9422. Min Act: -0.1700
Data Index: 2188093 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.9110. Min Act: -0.1700
Data Index: 6159136 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.9110. Min Act: -0.1700
Data Index: 3711485 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8797. Min Act: -0.1700
Data Index: 8164088 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8797. Min Act: -0.1700
Data Index: 2746138 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8797. Min Act: -0.1700
Data Index: 6406029 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8485. Min Act: -0.1700
Data Index: 3501916 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8485. Min Act: -0.1700
Data Index: 3789993 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8172. Min Act: -0.1700
Data Index: 5881673 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8485. Min Act: -0.1700
Data Index: 3588744 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8485. Min Act: -0.1700
Data Index: 3812637 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8172. Min Act: -0.1700
Data Index: 473516 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8172. Min Act: -0.1700
Data Index: 7650662 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3485. Min Range: -6.3485
Max Act: 5.8172. Min Act: -0.1700
Data Index: 8062015 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19