Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.7496. Min Act: -0.1700
Data Index: 7549681 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.7183. Min Act: -0.1700
Data Index: 4541507 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.7183. Min Act: -0.1700
Data Index: 4387527 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.7183. Min Act: -0.1700
Data Index: 532179 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.6871. Min Act: -0.1700
Data Index: 2923071 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.6871. Min Act: -0.1700
Data Index: 6654679 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.6246. Min Act: -0.1700
Data Index: 792789 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.5933. Min Act: -0.1700
Data Index: 2618054 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.5933. Min Act: -0.1700
Data Index: 7058230 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.5308. Min Act: -0.1700
Data Index: 2321079 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.5621. Min Act: -0.1700
Data Index: 1623493 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.5308. Min Act: -0.1700
Data Index: 7630276 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.4996. Min Act: -0.1700
Data Index: 5190786 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.4996. Min Act: -0.1700
Data Index: 7146058 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.4996. Min Act: -0.1700
Data Index: 1897177 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.4996. Min Act: -0.1700
Data Index: 8644258 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.4996. Min Act: -0.1700
Data Index: 5049566 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.4683. Min Act: -0.1700
Data Index: 1210198 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.4683. Min Act: -0.1700
Data Index: 1897188 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7496. Min Range: -5.7496
Max Act: 5.4683. Min Act: -0.1700
Data Index: 2548927 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19