Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6048. Min Range: -8.6048
Max Act: 8.6048. Min Act: -0.1700
Data Index: 4744883 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6048. Min Range: -8.6048
Max Act: 8.3548. Min Act: -0.1700
Data Index: 4503564 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6048. Min Range: -8.6048
Max Act: 8.2298. Min Act: -0.1700
Data Index: 333554 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6048. Min Range: -8.6048
Max Act: 8.2610. Min Act: -0.1700
Data Index: 2742697 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6048. Min Range: -8.6048
Max Act: 8.2298. Min Act: -0.1700
Data Index: 3200757 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6048. Min Range: -8.6048
Max Act: 8.0423. Min Act: -0.1700
Data Index: 2772753 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6048. Min Range: -8.6048
Max Act: 8.0423. Min Act: -0.1700
Data Index: 7519988 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6048. Min Range: -8.6048
Max Act: 8.0110. Min Act: -0.1700
Data Index: 4888808 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.8860. Min Act: -0.1700
Data Index: 2031494 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.9485. Min Act: -0.1700
Data Index: 4090929 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.9173. Min Act: -0.1700
Data Index: 5451585 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.8860. Min Act: -0.1700
Data Index: 6827966 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.9173. Min Act: -0.1700
Data Index: 7039099 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.8548. Min Act: -0.1700
Data Index: 8727014 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.8548. Min Act: -0.1700
Data Index: 1677764 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.8235. Min Act: -0.1700
Data Index: 2968830 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.8235. Min Act: -0.1700
Data Index: 398232 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.7923. Min Act: -0.1700
Data Index: 7489325 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.7923. Min Act: -0.1700
Data Index: 1241498 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6048. Min Range: -8.6048
Max Act: 7.7923. Min Act: -0.1700
Data Index: 3882218 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19