Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 597 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0932. Min Range: -6.0932
Max Act: 6.0932. Min Act: -0.1700
Data Index: 7082854 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0932. Min Range: -6.0932
Max Act: 6.0307. Min Act: -0.1700
Data Index: 6994650 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.9995. Min Act: -0.1700
Data Index: 6766444 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.9995. Min Act: -0.1700
Data Index: 4959222 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.8745. Min Act: -0.1700
Data Index: 7523380 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.8120. Min Act: -0.1700
Data Index: 8607250 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.8120. Min Act: -0.1700
Data Index: 7455869 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.8120. Min Act: -0.1700
Data Index: 5191831 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.7807. Min Act: -0.1700
Data Index: 5526484 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.7495. Min Act: -0.1700
Data Index: 4258948 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.7495. Min Act: -0.1700
Data Index: 3233809 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.7182. Min Act: -0.1700
Data Index: 1369244 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.7182. Min Act: -0.1700
Data Index: 7387896 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.7182. Min Act: -0.1700
Data Index: 7225736 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.6870. Min Act: -0.1700
Data Index: 7250475 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.6870. Min Act: -0.1700
Data Index: 116803 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.6870. Min Act: -0.1700
Data Index: 397732 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.6870. Min Act: -0.1700
Data Index: 2308024 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.6870. Min Act: -0.1700
Data Index: 209790 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0932. Min Range: -6.0932
Max Act: 5.6557. Min Act: -0.1700
Data Index: 8468334 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19