Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0834. Min Range: -5.0834
Max Act: 5.0834. Min Act: -0.1700
Data Index: 5362631 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.9584. Min Act: -0.1700
Data Index: 4553651 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.9272. Min Act: -0.1700
Data Index: 2898993 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.8334. Min Act: -0.1700
Data Index: 6776979 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.8647. Min Act: -0.1700
Data Index: 7985912 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.8647. Min Act: -0.1700
Data Index: 6385622 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.8022. Min Act: -0.1700
Data Index: 3386687 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.8022. Min Act: -0.1700
Data Index: 5150633 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7709. Min Act: -0.1700
Data Index: 4319987 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.8022. Min Act: -0.1700
Data Index: 2585884 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7709. Min Act: -0.1700
Data Index: 2742104 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7709. Min Act: -0.1700
Data Index: 1618609 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7084. Min Act: -0.1700
Data Index: 983611 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7084. Min Act: -0.1700
Data Index: 4326642 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7084. Min Act: -0.1700
Data Index: 5858740 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7397. Min Act: -0.1700
Data Index: 6256789 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7397. Min Act: -0.1700
Data Index: 3012908 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7397. Min Act: -0.1700
Data Index: 5555893 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.6772. Min Act: -0.1700
Data Index: 5128865 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0834. Min Range: -5.0834
Max Act: 4.7084. Min Act: -0.1700
Data Index: 5146937 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19