Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5742 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.9798. Min Act: -0.1700
Data Index: 342012 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.9486. Min Act: -0.1700
Data Index: 6405659 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.8236. Min Act: -0.1700
Data Index: 7353529 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.8236. Min Act: -0.1700
Data Index: 4884374 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.7611. Min Act: -0.1700
Data Index: 4057724 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.7923. Min Act: -0.1700
Data Index: 8530037 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.7923. Min Act: -0.1700
Data Index: 4061159 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.7298. Min Act: -0.1700
Data Index: 5446250 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.7611. Min Act: -0.1700
Data Index: 2072374 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.7298. Min Act: -0.1700
Data Index: 696383 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.7298. Min Act: -0.1700
Data Index: 605204 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6986. Min Act: -0.1700
Data Index: 2864600 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6673. Min Act: -0.1700
Data Index: 6817368 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6986. Min Act: -0.1700
Data Index: 4129468 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6673. Min Act: -0.1700
Data Index: 3354643 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6673. Min Act: -0.1700
Data Index: 610408 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6673. Min Act: -0.1700
Data Index: 1829775 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6673. Min Act: -0.1700
Data Index: 4114567 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6673. Min Act: -0.1700
Data Index: 6275350 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9798. Min Range: -4.9798
Max Act: 4.6673. Min Act: -0.1700
Data Index: 3979972 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19