Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1727 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.9298. Min Act: -0.1700
Data Index: 5365888 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.8673. Min Act: -0.1700
Data Index: 1089689 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.7735. Min Act: -0.1700
Data Index: 1322527 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.7110. Min Act: -0.1700
Data Index: 4507645 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.7110. Min Act: -0.1700
Data Index: 4193983 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.6798. Min Act: -0.1700
Data Index: 8544225 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.6798. Min Act: -0.1700
Data Index: 635907 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.6485. Min Act: -0.1700
Data Index: 4959664 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.6485. Min Act: -0.1700
Data Index: 5571569 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.6485. Min Act: -0.1700
Data Index: 851088 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.5548. Min Act: -0.1700
Data Index: 3027673 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.5860. Min Act: -0.1700
Data Index: 8492017 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.5548. Min Act: -0.1700
Data Index: 7962371 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.5548. Min Act: -0.1700
Data Index: 4552523 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2661200 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2450385 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.5235. Min Act: -0.1700
Data Index: 3690626 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.4923. Min Act: -0.1700
Data Index: 1024518 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.4923. Min Act: -0.1700
Data Index: 4119509 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9298. Min Range: -5.9298
Max Act: 5.4923. Min Act: -0.1700
Data Index: 1402769 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19