Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4790 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.3647. Min Act: -0.1700
Data Index: 5537153 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0664. Min Act: -0.1700
Data Index: 2180786 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0664. Min Act: -0.1700
Data Index: 3519322 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 5959894 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 2259707 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 2659720 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 1760952 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 3214456 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 3042870 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 1463822 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 3478589 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 5034622 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 4796406 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 2636500 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 2565232 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 5265051 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 1370118 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 4963453 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 2538857 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3647. Min Range: -2.3647
Max Act: 2.0495. Min Act: -0.1700
Data Index: 1205912 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19