Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 824 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7799. Min Act: -0.1700
Data Index: 4115224 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7799. Min Act: -0.1700
Data Index: 8670756 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3826951 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 168927 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 5702273 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 7757529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 1295518 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 2127666 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 6621813 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3852525 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 2926177 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 6280265 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 2000919 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 6279806 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3292897 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3150436 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 2223187 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3130705 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 6051940 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7799. Min Range: -4.7799
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3041303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19