Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4406. Min Range: -6.4406
Max Act: 6.4406. Min Act: -0.1700
Data Index: 3773888 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4406. Min Range: -6.4406
Max Act: 6.1281. Min Act: -0.1700
Data Index: 8128901 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4406. Min Range: -6.4406
Max Act: 6.0968. Min Act: -0.1700
Data Index: 5826396 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4406. Min Range: -6.4406
Max Act: 6.0343. Min Act: -0.1700
Data Index: 2927526 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.9718. Min Act: -0.1700
Data Index: 1746462 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4406. Min Range: -6.4406
Max Act: 6.0031. Min Act: -0.1700
Data Index: 4533972 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.9718. Min Act: -0.1700
Data Index: 3868725 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.9718. Min Act: -0.1700
Data Index: 7960654 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.9718. Min Act: -0.1700
Data Index: 1150686 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4406. Min Range: -6.4406
Max Act: 6.0031. Min Act: -0.1700
Data Index: 6400981 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.9718. Min Act: -0.1700
Data Index: 1524145 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.9406. Min Act: -0.1700
Data Index: 752624 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.9093. Min Act: -0.1700
Data Index: 8376685 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.9093. Min Act: -0.1700
Data Index: 3174262 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.8781. Min Act: -0.1700
Data Index: 6845726 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.8781. Min Act: -0.1700
Data Index: 803558 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.8781. Min Act: -0.1700
Data Index: 8228936 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.8781. Min Act: -0.1700
Data Index: 3393976 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.8468. Min Act: -0.1700
Data Index: 2248947 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4406. Min Range: -6.4406
Max Act: 5.8156. Min Act: -0.1700
Data Index: 3717266 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19