Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1215 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1323. Min Range: -5.1323
Max Act: 5.1323. Min Act: -0.1700
Data Index: 6569671 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1323. Min Range: -5.1323
Max Act: 5.1323. Min Act: -0.1700
Data Index: 2649056 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1323. Min Range: -5.1323
Max Act: 5.1010. Min Act: -0.1700
Data Index: 7099411 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1323. Min Range: -5.1323
Max Act: 5.1010. Min Act: -0.1700
Data Index: 376392 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1323. Min Range: -5.1323
Max Act: 5.0385. Min Act: -0.1700
Data Index: 8446296 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1323. Min Range: -5.1323
Max Act: 5.0073. Min Act: -0.1700
Data Index: 7247128 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1323. Min Range: -5.1323
Max Act: 5.0073. Min Act: -0.1700
Data Index: 7135519 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1323. Min Range: -5.1323
Max Act: 5.0073. Min Act: -0.1700
Data Index: 7981386 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9760. Min Act: -0.1700
Data Index: 7453855 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9760. Min Act: -0.1700
Data Index: 8348838 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9760. Min Act: -0.1700
Data Index: 5104097 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9448. Min Act: -0.1700
Data Index: 3812162 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9135. Min Act: -0.1700
Data Index: 7139042 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9448. Min Act: -0.1700
Data Index: 5330018 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9760. Min Act: -0.1700
Data Index: 1389010 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9448. Min Act: -0.1700
Data Index: 812978 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9448. Min Act: -0.1700
Data Index: 3634814 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9135. Min Act: -0.1700
Data Index: 2920258 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9760. Min Act: -0.1700
Data Index: 2920255 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1323. Min Range: -5.1323
Max Act: 4.9448. Min Act: -0.1700
Data Index: 8201280 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19