Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2481 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.9665. Min Act: -0.1700
Data Index: 4260527 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.8727. Min Act: -0.1700
Data Index: 4858978 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.8414. Min Act: -0.1700
Data Index: 7519041 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.8414. Min Act: -0.1700
Data Index: 59450 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.8101. Min Act: -0.1700
Data Index: 3007612 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.8101. Min Act: -0.1700
Data Index: 4378087 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.8101. Min Act: -0.1700
Data Index: 1841930 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7789. Min Act: -0.1700
Data Index: 5648103 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7476. Min Act: -0.1700
Data Index: 3404181 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7476. Min Act: -0.1700
Data Index: 6770834 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7476. Min Act: -0.1700
Data Index: 5000060 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7789. Min Act: -0.1700
Data Index: 6019656 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7476. Min Act: -0.1700
Data Index: 7806039 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7476. Min Act: -0.1700
Data Index: 7899825 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7163. Min Act: -0.1700
Data Index: 1881595 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7789. Min Act: -0.1700
Data Index: 7658300 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7163. Min Act: -0.1700
Data Index: 3623721 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7163. Min Act: -0.1700
Data Index: 4214497 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7476. Min Act: -0.1700
Data Index: 5536119 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9665. Min Range: -3.9665
Max Act: 3.7163. Min Act: -0.1700
Data Index: 1339743 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19