Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2031 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7666. Min Range: -8.7666
Max Act: 8.7666. Min Act: -0.1700
Data Index: 7701990 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7666. Min Range: -8.7666
Max Act: 8.4541. Min Act: -0.1700
Data Index: 4842740 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7666. Min Range: -8.7666
Max Act: 8.1416. Min Act: -0.1700
Data Index: 4655371 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7666. Min Range: -8.7666
Max Act: 8.1416. Min Act: -0.1700
Data Index: 2053063 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7666. Min Range: -8.7666
Max Act: 8.0791. Min Act: -0.1700
Data Index: 2002467 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7666. Min Range: -8.7666
Max Act: 8.0166. Min Act: -0.1700
Data Index: 1030045 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7666. Min Range: -8.7666
Max Act: 8.0166. Min Act: -0.1700
Data Index: 810756 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.9541. Min Act: -0.1700
Data Index: 4842745 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.8916. Min Act: -0.1700
Data Index: 2661704 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.7978. Min Act: -0.1700
Data Index: 2138432 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.7978. Min Act: -0.1700
Data Index: 7394088 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.7666. Min Act: -0.1700
Data Index: 4817110 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.7666. Min Act: -0.1700
Data Index: 5007605 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.7666. Min Act: -0.1700
Data Index: 3897241 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.7353. Min Act: -0.1700
Data Index: 1071398 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.7353. Min Act: -0.1700
Data Index: 3638537 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.6728. Min Act: -0.1700
Data Index: 1710675 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.6728. Min Act: -0.1700
Data Index: 6375018 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.6416. Min Act: -0.1700
Data Index: 3109493 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7666. Min Range: -8.7666
Max Act: 7.6416. Min Act: -0.1700
Data Index: 6114262 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19