Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.7991. Min Act: -0.1700
Data Index: 1505837 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.7366. Min Act: -0.1700
Data Index: 1206373 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.7366. Min Act: -0.1700
Data Index: 8703345 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.6741. Min Act: -0.1700
Data Index: 2875234 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.6116. Min Act: -0.1700
Data Index: 2009612 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.6116. Min Act: -0.1700
Data Index: 685927 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.6741. Min Act: -0.1700
Data Index: 825214 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.6116. Min Act: -0.1700
Data Index: 8651232 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.5491. Min Act: -0.1700
Data Index: 6221852 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.6116. Min Act: -0.1700
Data Index: 3006755 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.6741. Min Act: -0.1700
Data Index: 177903 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.5491. Min Act: -0.1700
Data Index: 3443284 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.5491. Min Act: -0.1700
Data Index: 7554822 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.5491. Min Act: -0.1700
Data Index: 2985263 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.5491. Min Act: -0.1700
Data Index: 2367574 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.4241. Min Act: -0.1700
Data Index: 3084704 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.4866. Min Act: -0.1700
Data Index: 7738382 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.4866. Min Act: -0.1700
Data Index: 764501 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.4866. Min Act: -0.1700
Data Index: 2829509 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7991. Min Range: -9.7991
Max Act: 9.4866. Min Act: -0.1700
Data Index: 8216635 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19