Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1614 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1639. Min Range: -5.1639
Max Act: 5.1639. Min Act: -0.1700
Data Index: 8619029 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1639. Min Range: -5.1639
Max Act: 5.1014. Min Act: -0.1700
Data Index: 693951 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1639. Min Range: -5.1639
Max Act: 5.1014. Min Act: -0.1700
Data Index: 7235238 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1639. Min Range: -5.1639
Max Act: 5.0389. Min Act: -0.1700
Data Index: 3534682 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1639. Min Range: -5.1639
Max Act: 5.0389. Min Act: -0.1700
Data Index: 1676080 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1639. Min Range: -5.1639
Max Act: 5.0389. Min Act: -0.1700
Data Index: 7890804 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1639. Min Range: -5.1639
Max Act: 5.0077. Min Act: -0.1700
Data Index: 7026100 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1639. Min Range: -5.1639
Max Act: 5.0077. Min Act: -0.1700
Data Index: 290021 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9764. Min Act: -0.1700
Data Index: 5887787 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9764. Min Act: -0.1700
Data Index: 1345208 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9764. Min Act: -0.1700
Data Index: 802448 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9452. Min Act: -0.1700
Data Index: 3572526 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9139. Min Act: -0.1700
Data Index: 7519123 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9139. Min Act: -0.1700
Data Index: 3468353 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9139. Min Act: -0.1700
Data Index: 4211673 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9139. Min Act: -0.1700
Data Index: 6264649 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.8514. Min Act: -0.1700
Data Index: 3232502 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9139. Min Act: -0.1700
Data Index: 2121639 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9139. Min Act: -0.1700
Data Index: 1330719 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1639. Min Range: -5.1639
Max Act: 4.9139. Min Act: -0.1700
Data Index: 683211 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19