Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.3762. Min Act: -0.1700
Data Index: 1315752 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.4075. Min Act: -0.1700
Data Index: 6994337 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.3450. Min Act: -0.1700
Data Index: 6683535 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.3137. Min Act: -0.1700
Data Index: 2307185 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.3450. Min Act: -0.1700
Data Index: 7246636 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.3137. Min Act: -0.1700
Data Index: 1294438 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.1887. Min Act: -0.1700
Data Index: 8324841 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.2200. Min Act: -0.1700
Data Index: 1147445 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.1887. Min Act: -0.1700
Data Index: 6284499 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.1887. Min Act: -0.1700
Data Index: 1931039 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.1575. Min Act: -0.1700
Data Index: 8191141 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.1262. Min Act: -0.1700
Data Index: 873668 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.1575. Min Act: -0.1700
Data Index: 4148171 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.1575. Min Act: -0.1700
Data Index: 572980 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.0950. Min Act: -0.1700
Data Index: 1876336 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.0637. Min Act: -0.1700
Data Index: 6704595 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.0950. Min Act: -0.1700
Data Index: 3165921 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.0637. Min Act: -0.1700
Data Index: 7381727 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.0950. Min Act: -0.1700
Data Index: 7897066 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4075. Min Range: -6.4075
Max Act: 6.0950. Min Act: -0.1700
Data Index: 5176833 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19