Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.2857. Min Act: -0.1700
Data Index: 164523 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.2544. Min Act: -0.1700
Data Index: 1762960 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.2544. Min Act: -0.1700
Data Index: 3750610 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.2544. Min Act: -0.1700
Data Index: 1215573 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.2232. Min Act: -0.1700
Data Index: 915180 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.1919. Min Act: -0.1700
Data Index: 6571700 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.1919. Min Act: -0.1700
Data Index: 3808227 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.1294. Min Act: -0.1700
Data Index: 253439 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.1607. Min Act: -0.1700
Data Index: 1056655 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.1294. Min Act: -0.1700
Data Index: 5298800 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0982. Min Act: -0.1700
Data Index: 7250220 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0982. Min Act: -0.1700
Data Index: 8672619 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0982. Min Act: -0.1700
Data Index: 7259728 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0982. Min Act: -0.1700
Data Index: 4964108 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0669. Min Act: -0.1700
Data Index: 4532751 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0357. Min Act: -0.1700
Data Index: 8188372 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0669. Min Act: -0.1700
Data Index: 2235001 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0357. Min Act: -0.1700
Data Index: 6974530 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0669. Min Act: -0.1700
Data Index: 164875 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2857. Min Range: -5.2857
Max Act: 5.0357. Min Act: -0.1700
Data Index: 6937837 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19