Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2356 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.7760. Min Act: -0.1700
Data Index: 1407883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.7448. Min Act: -0.1700
Data Index: 6537718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.7448. Min Act: -0.1699
Data Index: 4682210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.7135. Min Act: -0.1700
Data Index: 6240750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.7135. Min Act: -0.1700
Data Index: 4945668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 4814524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6509. Min Act: -0.1700
Data Index: 1436960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 5178781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6509. Min Act: -0.1700
Data Index: 5178350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 4945855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 1942373 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 8087903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 4870041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 5929419 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 8036241 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1699
Data Index: 6254580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6509. Min Act: -0.1700
Data Index: 1702850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 3729614 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 3620569 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6822. Min Act: -0.1700
Data Index: 3599888 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19