Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2173. Min Range: -4.2173
Max Act: 4.2173. Min Act: -0.1700
Data Index: 5727329 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2173. Min Range: -4.2173
Max Act: 4.1860. Min Act: -0.1700
Data Index: 6858852 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2173. Min Range: -4.2173
Max Act: 4.0297. Min Act: -0.1700
Data Index: 3943007 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2173. Min Range: -4.2173
Max Act: 4.0297. Min Act: -0.1700
Data Index: 8774130 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.9672. Min Act: -0.1700
Data Index: 3943006 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.9360. Min Act: -0.1700
Data Index: 4520782 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.9360. Min Act: -0.1700
Data Index: 2729862 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.9047. Min Act: -0.1700
Data Index: 7958359 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8734. Min Act: -0.1700
Data Index: 1226103 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.9047. Min Act: -0.1700
Data Index: 583336 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8734. Min Act: -0.1700
Data Index: 7870050 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8734. Min Act: -0.1700
Data Index: 766265 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8734. Min Act: -0.1700
Data Index: 2959301 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.9047. Min Act: -0.1700
Data Index: 2611012 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8734. Min Act: -0.1700
Data Index: 705295 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8422. Min Act: -0.1700
Data Index: 1126927 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8422. Min Act: -0.1700
Data Index: 2729861 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8109. Min Act: -0.1700
Data Index: 5161094 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8109. Min Act: -0.1700
Data Index: 1888934 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2173. Min Range: -4.2173
Max Act: 3.8109. Min Act: -0.1700
Data Index: 1376600 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19