Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 181 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.3912. Min Act: -0.1700
Data Index: 8711882 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.2037. Min Act: -0.1700
Data Index: 3960941 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.2037. Min Act: -0.1700
Data Index: 758649 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.2037. Min Act: -0.1700
Data Index: 3345539 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.1412. Min Act: -0.1700
Data Index: 4069550 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.1412. Min Act: -0.1700
Data Index: 7816151 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0787. Min Act: -0.1700
Data Index: 5541112 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0787. Min Act: -0.1700
Data Index: 4133138 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0787. Min Act: -0.1700
Data Index: 4098374 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0787. Min Act: -0.1700
Data Index: 1045676 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0787. Min Act: -0.1700
Data Index: 2037397 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0787. Min Act: -0.1700
Data Index: 4135335 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0162. Min Act: -0.1700
Data Index: 4457631 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0162. Min Act: -0.1700
Data Index: 8372500 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0162. Min Act: -0.1700
Data Index: 283800 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0162. Min Act: -0.1700
Data Index: 1069545 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0162. Min Act: -0.1700
Data Index: 687052 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0162. Min Act: -0.1700
Data Index: 3716608 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0162. Min Act: -0.1700
Data Index: 5303585 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3912. Min Range: -7.3912
Max Act: 7.0162. Min Act: -0.1700
Data Index: 200158 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19