Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 163 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0000. Min Range: -5.0000
Max Act: 5.0000. Min Act: -0.1700
Data Index: 5605628 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.7188. Min Act: -0.1700
Data Index: 5997096 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.6563. Min Act: -0.1700
Data Index: 3055967 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.6563. Min Act: -0.1700
Data Index: 2626437 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.6563. Min Act: -0.1700
Data Index: 3023455 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.5625. Min Act: -0.1700
Data Index: 451772 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.5000. Min Act: -0.1700
Data Index: 2926712 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.4688. Min Act: -0.1700
Data Index: 7889040 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.4688. Min Act: -0.1700
Data Index: 6458542 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1540393 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.4375. Min Act: -0.1700
Data Index: 5456531 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3750. Min Act: -0.1700
Data Index: 5420798 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3750. Min Act: -0.1700
Data Index: 1584145 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3750. Min Act: -0.1700
Data Index: 8669737 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3750. Min Act: -0.1700
Data Index: 4909926 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3125. Min Act: -0.1700
Data Index: 1500086 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3750. Min Act: -0.1700
Data Index: 2871065 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3125. Min Act: -0.1700
Data Index: 1084939 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3438. Min Act: -0.1700
Data Index: 3028131 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0000. Min Range: -5.0000
Max Act: 4.3438. Min Act: -0.1700
Data Index: 4736595 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19