Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4573 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.4047. Min Act: -0.1700
Data Index: 7183022 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.4047. Min Act: -0.1700
Data Index: 7337442 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.3422. Min Act: -0.1700
Data Index: 7116346 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.3422. Min Act: -0.1700
Data Index: 5010797 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.3109. Min Act: -0.1700
Data Index: 362612 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.2484. Min Act: -0.1700
Data Index: 2648405 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.2484. Min Act: -0.1700
Data Index: 645027 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1859. Min Act: -0.1700
Data Index: 3927449 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1859. Min Act: -0.1700
Data Index: 7992697 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1859. Min Act: -0.1700
Data Index: 3903848 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1547. Min Act: -0.1700
Data Index: 2391688 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1547. Min Act: -0.1700
Data Index: 4472662 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.0922. Min Act: -0.1700
Data Index: 2827863 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1234. Min Act: -0.1700
Data Index: 2122411 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.0922. Min Act: -0.1700
Data Index: 4577648 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.0922. Min Act: -0.1700
Data Index: 3358658 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.0922. Min Act: -0.1700
Data Index: 7133382 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.0609. Min Act: -0.1700
Data Index: 5242013 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.0609. Min Act: -0.1700
Data Index: 6910528 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.0609. Min Act: -0.1700
Data Index: 4371024 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19