Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3656. Min Range: -7.3656
Max Act: 7.3656. Min Act: -0.1700
Data Index: 6055546 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.7406. Min Act: -0.1700
Data Index: 6979159 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.5531. Min Act: -0.1700
Data Index: 240928 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.5218. Min Act: -0.1700
Data Index: 7712439 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.4593. Min Act: -0.1700
Data Index: 6928218 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.4281. Min Act: -0.1700
Data Index: 8169642 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.3968. Min Act: -0.1700
Data Index: 3086402 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.3343. Min Act: -0.1700
Data Index: 6322821 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.3031. Min Act: -0.1700
Data Index: 4562985 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.3031. Min Act: -0.1700
Data Index: 6089011 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.3031. Min Act: -0.1700
Data Index: 7039897 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.3031. Min Act: -0.1700
Data Index: 8829226 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.2718. Min Act: -0.1700
Data Index: 1137209 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.2718. Min Act: -0.1700
Data Index: 7945417 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.2718. Min Act: -0.1700
Data Index: 7436660 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.2093. Min Act: -0.1700
Data Index: 6634400 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.2406. Min Act: -0.1700
Data Index: 1450633 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.2406. Min Act: -0.1700
Data Index: 8028931 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.2406. Min Act: -0.1700
Data Index: 4318409 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3656. Min Range: -7.3656
Max Act: 6.2093. Min Act: -0.1700
Data Index: 6132829 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19