Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2189. Min Range: -5.2189
Max Act: 5.2189. Min Act: -0.1700
Data Index: 3118962 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2189. Min Range: -5.2189
Max Act: 5.1564. Min Act: -0.1700
Data Index: 1884459 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2189. Min Range: -5.2189
Max Act: 5.0002. Min Act: -0.1700
Data Index: 3063292 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.9689. Min Act: -0.1700
Data Index: 3339741 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.9689. Min Act: -0.1700
Data Index: 5607640 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.8752. Min Act: -0.1700
Data Index: 1488317 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.8127. Min Act: -0.1700
Data Index: 4682577 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.7502. Min Act: -0.1700
Data Index: 6555961 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.6877. Min Act: -0.1700
Data Index: 5757251 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.7502. Min Act: -0.1700
Data Index: 7552153 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.6877. Min Act: -0.1700
Data Index: 341333 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.6564. Min Act: -0.1700
Data Index: 5169659 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.6252. Min Act: -0.1700
Data Index: 3574386 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.6252. Min Act: -0.1700
Data Index: 6981361 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.5939. Min Act: -0.1700
Data Index: 6859434 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.5627. Min Act: -0.1700
Data Index: 2642472 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.5314. Min Act: -0.1700
Data Index: 5591718 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.5314. Min Act: -0.1700
Data Index: 8726159 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.5314. Min Act: -0.1700
Data Index: 5265179 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2189. Min Range: -5.2189
Max Act: 4.5314. Min Act: -0.1700
Data Index: 4227842 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19