Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2275 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8877. Min Act: -0.1700
Data Index: 929421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8564. Min Act: -0.1700
Data Index: 5606573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8564. Min Act: -0.1700
Data Index: 176743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8564. Min Act: -0.1700
Data Index: 3989015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8564. Min Act: -0.1700
Data Index: 6679863 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8252. Min Act: -0.1700
Data Index: 5652844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8252. Min Act: -0.1700
Data Index: 4706162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8252. Min Act: -0.1700
Data Index: 7634461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8252. Min Act: -0.1700
Data Index: 2073587 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8252. Min Act: -0.1700
Data Index: 1342164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8252. Min Act: -0.1700
Data Index: 3680829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7939. Min Act: -0.1700
Data Index: 7566370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7939. Min Act: -0.1700
Data Index: 1048892 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7939. Min Act: -0.1700
Data Index: 7794247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7939. Min Act: -0.1700
Data Index: 5799691 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7939. Min Act: -0.1700
Data Index: 2853465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7627. Min Act: -0.1700
Data Index: 3775724 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7627. Min Act: -0.1700
Data Index: 3862187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7627. Min Act: -0.1700
Data Index: 5819109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7314. Min Act: -0.1700
Data Index: 510483 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19