Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5707 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2998. Min Range: -6.2998
Max Act: 6.2998. Min Act: -0.1700
Data Index: 4642877 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2998. Min Range: -6.2998
Max Act: 6.1436. Min Act: -0.1700
Data Index: 4259425 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.9873. Min Act: -0.1700
Data Index: 580509 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.8623. Min Act: -0.1700
Data Index: 5738617 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.8623. Min Act: -0.1700
Data Index: 7622053 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.8311. Min Act: -0.1700
Data Index: 3314822 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7998. Min Act: -0.1700
Data Index: 648369 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7686. Min Act: -0.1700
Data Index: 7508977 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7998. Min Act: -0.1700
Data Index: 2012274 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7061. Min Act: -0.1700
Data Index: 841974 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.6123. Min Act: -0.1700
Data Index: 7230672 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.6123. Min Act: -0.1700
Data Index: 671488 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.5498. Min Act: -0.1700
Data Index: 4269981 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.5811. Min Act: -0.1700
Data Index: 3688668 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.5186. Min Act: -0.1700
Data Index: 8731171 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.5186. Min Act: -0.1700
Data Index: 6340228 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.5498. Min Act: -0.1700
Data Index: 5701897 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.5498. Min Act: -0.1700
Data Index: 5614904 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.5498. Min Act: -0.1700
Data Index: 1502905 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.5186. Min Act: -0.1700
Data Index: 75769 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19