Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2433 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.8611. Min Act: -0.1697
Data Index: 3573568 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7936. Min Act: -0.1698
Data Index: 5350211 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7853. Min Act: -0.1693
Data Index: 5350207 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7853. Min Act: -0.1700
Data Index: 5350209 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7603. Min Act: -0.1697
Data Index: 6428278 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7520. Min Act: -0.1700
Data Index: 7033930 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7437. Min Act: -0.1699
Data Index: 6090859 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7272. Min Act: -0.1699
Data Index: 7519926 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7272. Min Act: -0.1647
Data Index: 4958320 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7272. Min Act: -0.1700
Data Index: 5474764 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7108. Min Act: -0.1698
Data Index: 2792946 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7190. Min Act: -0.1700
Data Index: 2080137 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7108. Min Act: -0.1693
Data Index: 6987424 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7027. Min Act: -0.1696
Data Index: 2089646 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7027. Min Act: -0.1689
Data Index: 8217425 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7027. Min Act: -0.1693
Data Index: 5983381 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.7027. Min Act: -0.1698
Data Index: 3083541 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.6945. Min Act: -0.1700
Data Index: 2130563 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.6864. Min Act: -0.1699
Data Index: 4045617 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8611. Min Range: -0.8611
Max Act: 0.6864. Min Act: -0.1695
Data Index: 4774347 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19