Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1116. Min Range: -7.1116
Max Act: 7.1116. Min Act: -0.1700
Data Index: 8809510 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.8616. Min Act: -0.1700
Data Index: 492533 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.8616. Min Act: -0.1700
Data Index: 6228401 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.8616. Min Act: -0.1700
Data Index: 4128371 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.8616. Min Act: -0.1700
Data Index: 2634149 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.8616. Min Act: -0.1700
Data Index: 8584831 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.8303. Min Act: -0.1700
Data Index: 7694709 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.7991. Min Act: -0.1700
Data Index: 5445150 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.7678. Min Act: -0.1700
Data Index: 5804287 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.7366. Min Act: -0.1700
Data Index: 4322674 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6741. Min Act: -0.1700
Data Index: 1837386 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6428. Min Act: -0.1700
Data Index: 825003 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6428. Min Act: -0.1700
Data Index: 7957287 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6428. Min Act: -0.1700
Data Index: 4790958 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6116. Min Act: -0.1700
Data Index: 5333953 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6116. Min Act: -0.1700
Data Index: 5321780 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6116. Min Act: -0.1700
Data Index: 7339454 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6116. Min Act: -0.1700
Data Index: 376300 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.6116. Min Act: -0.1700
Data Index: 4088786 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1116. Min Range: -7.1116
Max Act: 6.5803. Min Act: -0.1700
Data Index: 1991470 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19