Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 863 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.6767. Min Act: -0.1700
Data Index: 5352931 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.6141. Min Act: -0.1700
Data Index: 7307110 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5828. Min Act: -0.1700
Data Index: 4527493 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5828. Min Act: -0.1700
Data Index: 3962750 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5671. Min Act: -0.1700
Data Index: 5208294 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5671. Min Act: -0.1700
Data Index: 1292858 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5515. Min Act: -0.1700
Data Index: 2583090 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5515. Min Act: -0.1700
Data Index: 5799474 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5358. Min Act: -0.1700
Data Index: 4188626 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5358. Min Act: -0.1700
Data Index: 713069 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5358. Min Act: -0.1700
Data Index: 6092181 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5202. Min Act: -0.1700
Data Index: 6237228 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5358. Min Act: -0.1700
Data Index: 3391619 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5202. Min Act: -0.1700
Data Index: 6835584 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5045. Min Act: -0.1700
Data Index: 1933179 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5202. Min Act: -0.1700
Data Index: 2724148 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5045. Min Act: -0.1700
Data Index: 4438313 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.4888. Min Act: -0.1700
Data Index: 5965890 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.5045. Min Act: -0.1700
Data Index: 1240027 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6767. Min Range: -3.6767
Max Act: 3.4732. Min Act: -0.1700
Data Index: 4468013 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19