Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1567 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.3761. Min Act: -0.1700
Data Index: 7188104 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.3418. Min Act: -0.1700
Data Index: 7654191 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.3086. Min Act: -0.1697
Data Index: 191071 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.3086. Min Act: -0.1700
Data Index: 7960646 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.3086. Min Act: -0.1699
Data Index: 7247844 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2955. Min Act: -0.1700
Data Index: 791626 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2955. Min Act: -0.1700
Data Index: 170929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2955. Min Act: -0.1700
Data Index: 5221573 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2890. Min Act: -0.1700
Data Index: 5439886 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2762. Min Act: -0.1700
Data Index: 5392446 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2762. Min Act: -0.1700
Data Index: 7666789 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2826. Min Act: -0.1700
Data Index: 7145091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2826. Min Act: -0.1678
Data Index: 8338777 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2699. Min Act: -0.1700
Data Index: 723139 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2636. Min Act: -0.1700
Data Index: 7599293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2636. Min Act: -0.1699
Data Index: 3418143 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2636. Min Act: -0.1700
Data Index: 501805 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2636. Min Act: -0.1700
Data Index: 583712 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2636. Min Act: -0.1700
Data Index: 7008010 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3761. Min Range: -0.3761
Max Act: 0.2636. Min Act: -0.1700
Data Index: 6847321 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19