Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 939 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1321. Min Range: -7.1321
Max Act: 7.1321. Min Act: -0.1700
Data Index: 7741406 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.9133. Min Act: -0.1700
Data Index: 5439838 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.7258. Min Act: -0.1700
Data Index: 2926148 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.6008. Min Act: -0.1700
Data Index: 7587676 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.6008. Min Act: -0.1700
Data Index: 1872333 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.6008. Min Act: -0.1700
Data Index: 2408728 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5696. Min Act: -0.1700
Data Index: 2539145 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5696. Min Act: -0.1700
Data Index: 7288115 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5383. Min Act: -0.1700
Data Index: 695341 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5383. Min Act: -0.1700
Data Index: 4147903 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5383. Min Act: -0.1700
Data Index: 8727200 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5383. Min Act: -0.1700
Data Index: 7517319 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5383. Min Act: -0.1700
Data Index: 4390115 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5071. Min Act: -0.1700
Data Index: 7776629 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5071. Min Act: -0.1700
Data Index: 8306954 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5071. Min Act: -0.1700
Data Index: 6790911 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.4758. Min Act: -0.1700
Data Index: 1655867 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5071. Min Act: -0.1700
Data Index: 5348605 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.5071. Min Act: -0.1700
Data Index: 384007 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1321. Min Range: -7.1321
Max Act: 6.4446. Min Act: -0.1700
Data Index: 6186915 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19