Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 736 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.6674. Min Act: -0.1700
Data Index: 6672951 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.5424. Min Act: -0.1700
Data Index: 2818448 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.5736. Min Act: -0.1700
Data Index: 2382305 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.5111. Min Act: -0.1700
Data Index: 4249865 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.4799. Min Act: -0.1700
Data Index: 3755581 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.5111. Min Act: -0.1700
Data Index: 8584884 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.5424. Min Act: -0.1700
Data Index: 5654255 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.4486. Min Act: -0.1700
Data Index: 8741948 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.4799. Min Act: -0.1700
Data Index: 1248185 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.4486. Min Act: -0.1700
Data Index: 2327839 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.4173. Min Act: -0.1700
Data Index: 3536178 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.4173. Min Act: -0.1700
Data Index: 658206 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.3861. Min Act: -0.1700
Data Index: 5930194 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.3861. Min Act: -0.1700
Data Index: 4795343 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.3548. Min Act: -0.1700
Data Index: 894285 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.3861. Min Act: -0.1700
Data Index: 5784410 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.3861. Min Act: -0.1700
Data Index: 8241194 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.3861. Min Act: -0.1700
Data Index: 7879310 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.3861. Min Act: -0.1700
Data Index: 4410227 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6674. Min Range: -4.6674
Max Act: 4.3548. Min Act: -0.1700
Data Index: 6777140 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19