Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2283 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8882. Min Act: -0.1700
Data Index: 8162503 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8723. Min Act: -0.1700
Data Index: 4045207 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8565. Min Act: -0.1700
Data Index: 7619474 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8406. Min Act: -0.1700
Data Index: 6435069 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8406. Min Act: -0.1700
Data Index: 5539535 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8406. Min Act: -0.1700
Data Index: 5392792 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8406. Min Act: -0.1700
Data Index: 8191927 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8406. Min Act: -0.1700
Data Index: 1576298 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8406. Min Act: -0.1700
Data Index: 5576991 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8406. Min Act: -0.1700
Data Index: 6616939 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8247. Min Act: -0.1700
Data Index: 2882718 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8247. Min Act: -0.1700
Data Index: 7251458 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8247. Min Act: -0.1700
Data Index: 873125 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8088. Min Act: -0.1700
Data Index: 7958666 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8088. Min Act: -0.1700
Data Index: 8037999 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8088. Min Act: -0.1700
Data Index: 4432651 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8088. Min Act: -0.1700
Data Index: 2684852 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.8088. Min Act: -0.1700
Data Index: 5008548 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.7928. Min Act: -0.1700
Data Index: 6591387 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8882. Min Range: -2.8882
Max Act: 2.7928. Min Act: -0.1700
Data Index: 167763 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19