Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4953. Min Act: -0.1700
Data Index: 615895 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4640. Min Act: -0.1700
Data Index: 2141655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4327. Min Act: -0.1700
Data Index: 6673108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4327. Min Act: -0.1700
Data Index: 8594709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4327. Min Act: -0.1700
Data Index: 5386349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4327. Min Act: -0.1700
Data Index: 1996937 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4013. Min Act: -0.1700
Data Index: 3061191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4013. Min Act: -0.1700
Data Index: 3636088 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4013. Min Act: -0.1700
Data Index: 1148093 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.4013. Min Act: -0.1700
Data Index: 8711018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3700. Min Act: -0.1700
Data Index: 7559946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3700. Min Act: -0.1700
Data Index: 71619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3700. Min Act: -0.1700
Data Index: 6092867 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3700. Min Act: -0.1700
Data Index: 6062907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3700. Min Act: -0.1700
Data Index: 366561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3700. Min Act: -0.1700
Data Index: 892872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3700. Min Act: -0.1700
Data Index: 3531239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3386. Min Act: -0.1700
Data Index: 4844615 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3386. Min Act: -0.1700
Data Index: 7105922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4953. Min Range: -3.4953
Max Act: 3.3386. Min Act: -0.1700
Data Index: 7333941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19