Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 106 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.9188. Min Act: -0.1700
Data Index: 6216449 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.9188. Min Act: -0.1700
Data Index: 2876311 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.8876. Min Act: -0.1700
Data Index: 491912 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.8563. Min Act: -0.1700
Data Index: 5864108 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.8251. Min Act: -0.1700
Data Index: 4162153 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.8251. Min Act: -0.1700
Data Index: 6898566 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7626. Min Act: -0.1700
Data Index: 5777763 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7626. Min Act: -0.1700
Data Index: 3598808 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7626. Min Act: -0.1700
Data Index: 6738300 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7626. Min Act: -0.1700
Data Index: 331584 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7626. Min Act: -0.1700
Data Index: 3080332 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7626. Min Act: -0.1700
Data Index: 7037132 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7626. Min Act: -0.1700
Data Index: 6320719 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7313. Min Act: -0.1700
Data Index: 2186399 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7313. Min Act: -0.1700
Data Index: 6765060 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7313. Min Act: -0.1700
Data Index: 4245196 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7313. Min Act: -0.1700
Data Index: 438277 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7001. Min Act: -0.1700
Data Index: 3207980 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5155698 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9188. Min Range: -5.9188
Max Act: 5.7001. Min Act: -0.1700
Data Index: 3421198 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19