Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1059 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1217. Min Range: -4.1217
Max Act: 4.1217. Min Act: -0.1700
Data Index: 8287606 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.8091. Min Act: -0.1700
Data Index: 5719690 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7778. Min Act: -0.1700
Data Index: 1917143 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7465. Min Act: -0.1700
Data Index: 3052424 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7465. Min Act: -0.1700
Data Index: 7664402 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7152. Min Act: -0.1700
Data Index: 8541939 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7465. Min Act: -0.1700
Data Index: 7112683 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7778. Min Act: -0.1700
Data Index: 3282054 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7465. Min Act: -0.1700
Data Index: 1179231 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7465. Min Act: -0.1700
Data Index: 6788138 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7465. Min Act: -0.1700
Data Index: 4875063 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.7152. Min Act: -0.1700
Data Index: 2849407 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.6840. Min Act: -0.1700
Data Index: 6889944 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.6840. Min Act: -0.1700
Data Index: 8440303 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.6840. Min Act: -0.1700
Data Index: 8001614 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.6840. Min Act: -0.1700
Data Index: 1389804 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.6840. Min Act: -0.1700
Data Index: 5597681 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.6840. Min Act: -0.1700
Data Index: 1389805 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.6527. Min Act: -0.1700
Data Index: 2458777 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.6527. Min Act: -0.1700
Data Index: 7177411 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19