Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6122. Min Range: -8.6122
Max Act: 8.6122. Min Act: -0.1700
Data Index: 3449876 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6122. Min Range: -8.6122
Max Act: 8.5497. Min Act: -0.1700
Data Index: 5656247 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6122. Min Range: -8.6122
Max Act: 8.4247. Min Act: -0.1700
Data Index: 5219238 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6122. Min Range: -8.6122
Max Act: 8.0185. Min Act: -0.1700
Data Index: 1702798 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6122. Min Range: -8.6122
Max Act: 8.0497. Min Act: -0.1700
Data Index: 3987377 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.9872. Min Act: -0.1700
Data Index: 644050 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.9560. Min Act: -0.1700
Data Index: 7851658 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.8935. Min Act: -0.1700
Data Index: 4912862 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.8622. Min Act: -0.1700
Data Index: 4905653 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7997. Min Act: -0.1700
Data Index: 2733026 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.8935. Min Act: -0.1700
Data Index: 1542422 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7997. Min Act: -0.1700
Data Index: 1009671 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7997. Min Act: -0.1700
Data Index: 2866035 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7685. Min Act: -0.1700
Data Index: 2473778 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7372. Min Act: -0.1700
Data Index: 5961178 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7997. Min Act: -0.1700
Data Index: 6497867 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7685. Min Act: -0.1700
Data Index: 3792631 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7997. Min Act: -0.1700
Data Index: 2857550 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7060. Min Act: -0.1700
Data Index: 2857551 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6122. Min Range: -8.6122
Max Act: 7.7372. Min Act: -0.1700
Data Index: 3235023 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19