Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4479 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6082. Min Range: -7.6082
Max Act: 7.6082. Min Act: -0.1700
Data Index: 845132 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6082. Min Range: -7.6082
Max Act: 7.3582. Min Act: -0.1700
Data Index: 6825705 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6082. Min Range: -7.6082
Max Act: 7.1707. Min Act: -0.1700
Data Index: 6184986 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6082. Min Range: -7.6082
Max Act: 7.0769. Min Act: -0.1700
Data Index: 2334446 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.8894. Min Act: -0.1700
Data Index: 5894052 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.8894. Min Act: -0.1700
Data Index: 6636482 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.8269. Min Act: -0.1700
Data Index: 4780935 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.8269. Min Act: -0.1700
Data Index: 5905478 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7957. Min Act: -0.1700
Data Index: 7613449 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7644. Min Act: -0.1700
Data Index: 8373446 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7644. Min Act: -0.1700
Data Index: 6172582 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7644. Min Act: -0.1700
Data Index: 4906569 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7644. Min Act: -0.1700
Data Index: 852869 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7332. Min Act: -0.1700
Data Index: 5921193 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7332. Min Act: -0.1700
Data Index: 702841 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7332. Min Act: -0.1700
Data Index: 915666 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7019. Min Act: -0.1700
Data Index: 4398388 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7332. Min Act: -0.1700
Data Index: 8810638 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7019. Min Act: -0.1700
Data Index: 7044157 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6082. Min Range: -7.6082
Max Act: 6.7019. Min Act: -0.1700
Data Index: 7508767 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19