Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.7269. Min Act: -0.1700
Data Index: 1036491 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.5707. Min Act: -0.1700
Data Index: 4705760 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.5394. Min Act: -0.1700
Data Index: 7158098 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.5082. Min Act: -0.1700
Data Index: 4453078 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.4769. Min Act: -0.1700
Data Index: 7872438 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.4769. Min Act: -0.1700
Data Index: 2764446 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.5082. Min Act: -0.1700
Data Index: 6618494 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.4769. Min Act: -0.1700
Data Index: 7420341 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.4769. Min Act: -0.1700
Data Index: 1420243 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.4457. Min Act: -0.1700
Data Index: 926258 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.4144. Min Act: -0.1700
Data Index: 5089846 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.4144. Min Act: -0.1700
Data Index: 4356771 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.4144. Min Act: -0.1700
Data Index: 3766892 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.3832. Min Act: -0.1700
Data Index: 4241041 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.3832. Min Act: -0.1700
Data Index: 1422760 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.3832. Min Act: -0.1700
Data Index: 1006717 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.3832. Min Act: -0.1700
Data Index: 8707131 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.3519. Min Act: -0.1700
Data Index: 3416774 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.3519. Min Act: -0.1700
Data Index: 3413171 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7269. Min Range: -4.7269
Max Act: 4.3519. Min Act: -0.1700
Data Index: 4045788 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19