Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2166 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.6531. Min Act: -0.1700
Data Index: 686761 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.6209. Min Act: -0.1700
Data Index: 8086404 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.6209. Min Act: -0.1700
Data Index: 8207892 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.5888. Min Act: -0.1700
Data Index: 1952470 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.5888. Min Act: -0.1700
Data Index: 1440730 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.5565. Min Act: -0.1700
Data Index: 7653308 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.5080. Min Act: -0.1700
Data Index: 5703037 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4918. Min Act: -0.1700
Data Index: 3733539 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4756. Min Act: -0.1700
Data Index: 6258636 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4431. Min Act: -0.1700
Data Index: 2849935 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4756. Min Act: -0.1700
Data Index: 6166502 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4756. Min Act: -0.1700
Data Index: 2374483 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4918. Min Act: -0.1700
Data Index: 7647868 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4594. Min Act: -0.1697
Data Index: 1315104 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4431. Min Act: -0.1700
Data Index: 1061541 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4431. Min Act: -0.1700
Data Index: 2636513 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4431. Min Act: -0.1700
Data Index: 60267 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4268. Min Act: -0.1700
Data Index: 6158285 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.4105. Min Act: -0.1700
Data Index: 6936712 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6531. Min Range: -2.6531
Max Act: 2.3942. Min Act: -0.1700
Data Index: 6346840 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19