Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4928. Min Range: -8.4928
Max Act: 8.4928. Min Act: -0.1700
Data Index: 3421490 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.9303. Min Act: -0.1700
Data Index: 8649501 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.8053. Min Act: -0.1700
Data Index: 2971056 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.8053. Min Act: -0.1700
Data Index: 3875311 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.7740. Min Act: -0.1700
Data Index: 4663724 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.7740. Min Act: -0.1700
Data Index: 2103059 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.7428. Min Act: -0.1700
Data Index: 3322799 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.7115. Min Act: -0.1700
Data Index: 8375705 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.6178. Min Act: -0.1700
Data Index: 5883251 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.6178. Min Act: -0.1700
Data Index: 369048 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.6178. Min Act: -0.1700
Data Index: 6929036 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5865. Min Act: -0.1700
Data Index: 2211983 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5865. Min Act: -0.1700
Data Index: 6475964 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5553. Min Act: -0.1700
Data Index: 5037725 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5553. Min Act: -0.1700
Data Index: 1884375 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5553. Min Act: -0.1700
Data Index: 1812505 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5240. Min Act: -0.1700
Data Index: 2870317 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5240. Min Act: -0.1700
Data Index: 5460219 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5240. Min Act: -0.1700
Data Index: 5149679 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4928. Min Range: -8.4928
Max Act: 7.5240. Min Act: -0.1700
Data Index: 5562660 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19