Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2079 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.5842. Min Act: -0.1700
Data Index: 900129 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.4904. Min Act: -0.1700
Data Index: 2381642 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.4279. Min Act: -0.1700
Data Index: 4300469 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.4279. Min Act: -0.1700
Data Index: 6951459 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.4279. Min Act: -0.1700
Data Index: 3342719 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.3342. Min Act: -0.1700
Data Index: 5431146 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.3029. Min Act: -0.1700
Data Index: 341521 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2717. Min Act: -0.1700
Data Index: 900108 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2717. Min Act: -0.1700
Data Index: 7341876 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2717. Min Act: -0.1700
Data Index: 379522 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2404. Min Act: -0.1700
Data Index: 2757243 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2404. Min Act: -0.1700
Data Index: 900130 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2092. Min Act: -0.1700
Data Index: 1520340 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2092. Min Act: -0.1700
Data Index: 284737 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2092. Min Act: -0.1700
Data Index: 1717519 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.1779. Min Act: -0.1700
Data Index: 8027966 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.1779. Min Act: -0.1700
Data Index: 900127 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2092. Min Act: -0.1700
Data Index: 4109419 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.2092. Min Act: -0.1700
Data Index: 4109420 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5842. Min Range: -5.5842
Max Act: 5.1779. Min Act: -0.1700
Data Index: 6274889 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19