Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.9007. Min Act: -0.1700
Data Index: 2423350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.8694. Min Act: -0.1700
Data Index: 270365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.8381. Min Act: -0.1700
Data Index: 8750632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.8694. Min Act: -0.1700
Data Index: 5403777 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.8694. Min Act: -0.1700
Data Index: 943319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.8381. Min Act: -0.1700
Data Index: 5048497 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.8069. Min Act: -0.1700
Data Index: 6414120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.7756. Min Act: -0.1700
Data Index: 7838690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.7756. Min Act: -0.1700
Data Index: 7373545 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.7756. Min Act: -0.1700
Data Index: 7126041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.7443. Min Act: -0.1700
Data Index: 3615588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.7443. Min Act: -0.1700
Data Index: 488390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.6817. Min Act: -0.1700
Data Index: 8102433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.7130. Min Act: -0.1700
Data Index: 1743228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.6817. Min Act: -0.1700
Data Index: 8126618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.6504. Min Act: -0.1700
Data Index: 4306104 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.6192. Min Act: -0.1700
Data Index: 8482107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.6192. Min Act: -0.1700
Data Index: 7991551 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.5879. Min Act: -0.1700
Data Index: 7998925 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9007. Min Range: -3.9007
Max Act: 3.5879. Min Act: -0.1700
Data Index: 1176203 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19