Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4619 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.5207. Min Act: -0.1700
Data Index: 4735667 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.3332. Min Act: -0.1700
Data Index: 5464889 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.2707. Min Act: -0.1700
Data Index: 7482304 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.2082. Min Act: -0.1700
Data Index: 1358894 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.2082. Min Act: -0.1700
Data Index: 7577070 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.2082. Min Act: -0.1700
Data Index: 2457179 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1769. Min Act: -0.1700
Data Index: 4612763 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1457. Min Act: -0.1700
Data Index: 6639389 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1144. Min Act: -0.1700
Data Index: 3466011 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1144. Min Act: -0.1700
Data Index: 21682 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1144. Min Act: -0.1700
Data Index: 146324 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1144. Min Act: -0.1700
Data Index: 4391929 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1144. Min Act: -0.1700
Data Index: 5397928 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1144. Min Act: -0.1700
Data Index: 4772070 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.1144. Min Act: -0.1700
Data Index: 4218546 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.0832. Min Act: -0.1700
Data Index: 4956155 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.0832. Min Act: -0.1700
Data Index: 3885067 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.0832. Min Act: -0.1700
Data Index: 1634864 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.0832. Min Act: -0.1700
Data Index: 1379689 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5207. Min Range: -5.5207
Max Act: 5.0832. Min Act: -0.1700
Data Index: 3911446 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19