Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 105 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.9935. Min Act: -0.1700
Data Index: 687821 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0247. Min Range: -5.0247
Max Act: 5.0247. Min Act: -0.1700
Data Index: 5303029 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.9622. Min Act: -0.1700
Data Index: 5773058 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.9935. Min Act: -0.1700
Data Index: 7887135 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.8372. Min Act: -0.1700
Data Index: 7791783 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.8372. Min Act: -0.1700
Data Index: 6256446 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.8372. Min Act: -0.1700
Data Index: 7488599 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.8060. Min Act: -0.1700
Data Index: 7108350 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7435. Min Act: -0.1700
Data Index: 8481838 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7435. Min Act: -0.1700
Data Index: 662472 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7122. Min Act: -0.1700
Data Index: 4134039 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7435. Min Act: -0.1700
Data Index: 112431 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7435. Min Act: -0.1700
Data Index: 4584747 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7122. Min Act: -0.1700
Data Index: 4883063 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7435. Min Act: -0.1700
Data Index: 8698359 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7122. Min Act: -0.1700
Data Index: 718447 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.6810. Min Act: -0.1700
Data Index: 4002133 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.6810. Min Act: -0.1700
Data Index: 7918586 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.7122. Min Act: -0.1700
Data Index: 1575341 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0247. Min Range: -5.0247
Max Act: 4.6810. Min Act: -0.1700
Data Index: 7798102 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19