Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.3424. Min Act: -0.1700
Data Index: 668906 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.1774. Min Act: -0.1700
Data Index: 4491179 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.1607. Min Act: -0.1700
Data Index: 1515176 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.1274. Min Act: -0.1700
Data Index: 3735125 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.1106. Min Act: -0.1700
Data Index: 2214410 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.1274. Min Act: -0.1700
Data Index: 3167492 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.1106. Min Act: -0.1700
Data Index: 6337626 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.1106. Min Act: -0.1700
Data Index: 1245857 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0771. Min Act: -0.1700
Data Index: 4988334 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0939. Min Act: -0.1700
Data Index: 2996997 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0771. Min Act: -0.1700
Data Index: 7048589 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0603. Min Act: -0.1700
Data Index: 7270165 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0267. Min Act: -0.1700
Data Index: 4893645 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0603. Min Act: -0.1700
Data Index: 986170 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0267. Min Act: -0.1700
Data Index: 3765869 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0435. Min Act: -0.1700
Data Index: 5942817 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0267. Min Act: -0.1700
Data Index: 6980251 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0603. Min Act: -0.1700
Data Index: 1417459 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3424. Min Range: -2.3424
Max Act: 2.0267. Min Act: -0.1700
Data Index: 6367418 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3424. Min Range: -2.3424
Max Act: 1.9929. Min Act: -0.1700
Data Index: 4000784 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19