Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4591 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6984. Min Act: -0.1700
Data Index: 3288593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6671. Min Act: -0.1700
Data Index: 7185862 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6671. Min Act: -0.1700
Data Index: 7522600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6671. Min Act: -0.1700
Data Index: 8506104 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6671. Min Act: -0.1700
Data Index: 761124 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 2500030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 119527 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 8510992 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 4079586 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 2028043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 4007686 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 1008226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 975411 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 3905988 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 232588 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 3723921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 3414603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 24568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 13982 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 3295567 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19