Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3119 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7756. Min Act: -0.1700
Data Index: 2630722 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7669. Min Act: -0.1700
Data Index: 6283575 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7756. Min Act: -0.1700
Data Index: 5432680 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7756. Min Act: -0.1700
Data Index: 4519323 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7237. Min Act: -0.1700
Data Index: 446077 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7237. Min Act: -0.1700
Data Index: 6517777 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7237. Min Act: -0.1700
Data Index: 4000627 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7151. Min Act: -0.1699
Data Index: 91038 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7237. Min Act: -0.1700
Data Index: 8140197 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6978. Min Act: -0.1700
Data Index: 5039510 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7064. Min Act: -0.1700
Data Index: 4686939 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.7064. Min Act: -0.1700
Data Index: 2924025 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6978. Min Act: -0.1700
Data Index: 6283574 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6891. Min Act: -0.1700
Data Index: 4280261 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6978. Min Act: -0.1700
Data Index: 1773136 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6891. Min Act: -0.1700
Data Index: 7201307 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6630. Min Act: -0.1689
Data Index: 2141607 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6804. Min Act: -0.1700
Data Index: 2799453 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6978. Min Act: -0.1700
Data Index: 4333574 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7756. Min Range: -1.7756
Max Act: 1.6804. Min Act: -0.1700
Data Index: 7011830 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19