Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1739 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.7117. Min Act: -0.1700
Data Index: 8249329 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.4930. Min Act: -0.1700
Data Index: 6441424 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.2742. Min Act: -0.1700
Data Index: 4657034 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.2742. Min Act: -0.1700
Data Index: 530500 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.2430. Min Act: -0.1700
Data Index: 4583630 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.2117. Min Act: -0.1700
Data Index: 1901599 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.1805. Min Act: -0.1700
Data Index: 2373658 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.1492. Min Act: -0.1700
Data Index: 40502 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.1492. Min Act: -0.1700
Data Index: 2864283 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.1492. Min Act: -0.1700
Data Index: 3595517 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.1179. Min Act: -0.1700
Data Index: 7319699 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.0554. Min Act: -0.1700
Data Index: 1862592 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.0867. Min Act: -0.1700
Data Index: 3122151 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.0554. Min Act: -0.1700
Data Index: 616804 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.0554. Min Act: -0.1700
Data Index: 2497648 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.0242. Min Act: -0.1700
Data Index: 1650677 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7117. Min Range: -4.7117
Max Act: 3.9929. Min Act: -0.1700
Data Index: 7310771 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.0242. Min Act: -0.1700
Data Index: 901180 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.0554. Min Act: -0.1700
Data Index: 1310601 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7117. Min Range: -4.7117
Max Act: 3.9929. Min Act: -0.1700
Data Index: 2094803 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19