Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1837. Min Act: -0.1700
Data Index: 7076292 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1525. Min Act: -0.1700
Data Index: 4914401 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1212. Min Act: -0.1700
Data Index: 8171508 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1212. Min Act: -0.1700
Data Index: 8391242 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1212. Min Act: -0.1700
Data Index: 6633953 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1212. Min Act: -0.1700
Data Index: 5053071 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0900. Min Act: -0.1700
Data Index: 8530078 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0900. Min Act: -0.1700
Data Index: 3991180 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0900. Min Act: -0.1700
Data Index: 3485585 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0900. Min Act: -0.1700
Data Index: 5168881 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0900. Min Act: -0.1700
Data Index: 5295963 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0587. Min Act: -0.1700
Data Index: 513859 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0587. Min Act: -0.1700
Data Index: 4395354 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0275. Min Act: -0.1700
Data Index: 5053072 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0275. Min Act: -0.1700
Data Index: 3991178 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7910708 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9962. Min Act: -0.1700
Data Index: 3991179 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9962. Min Act: -0.1700
Data Index: 6759010 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9962. Min Act: -0.1700
Data Index: 2936235 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9962. Min Act: -0.1700
Data Index: 7309030 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19