Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3114 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.5553. Min Act: -0.1700
Data Index: 8766992 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.5553. Min Act: -0.1700
Data Index: 1514914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.4928. Min Act: -0.1700
Data Index: 3639385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.4928. Min Act: -0.1700
Data Index: 4420515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.4928. Min Act: -0.1700
Data Index: 3647877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.4616. Min Act: -0.1700
Data Index: 1241978 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.4303. Min Act: -0.1700
Data Index: 268915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.4303. Min Act: -0.1700
Data Index: 4546044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3990. Min Act: -0.1700
Data Index: 3926998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3990. Min Act: -0.1700
Data Index: 4045630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3678. Min Act: -0.1700
Data Index: 6321533 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3678. Min Act: -0.1700
Data Index: 4719391 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3678. Min Act: -0.1700
Data Index: 4298505 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3365. Min Act: -0.1700
Data Index: 7325952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3053. Min Act: -0.1700
Data Index: 5791497 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3053. Min Act: -0.1700
Data Index: 3086684 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.3053. Min Act: -0.1700
Data Index: 5807093 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.2740. Min Act: -0.1700
Data Index: 1763912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.2740. Min Act: -0.1700
Data Index: 2707446 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5553. Min Range: -4.5553
Max Act: 4.2740. Min Act: -0.1700
Data Index: 5277402 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19