Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 699 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.9613. Min Act: -0.1700
Data Index: 6428324 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8988. Min Act: -0.1700
Data Index: 4161563 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8675. Min Act: -0.1700
Data Index: 8518541 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8363. Min Act: -0.1700
Data Index: 8111188 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8675. Min Act: -0.1700
Data Index: 2549851 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8363. Min Act: -0.1700
Data Index: 3844380 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8675. Min Act: -0.1699
Data Index: 5624612 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8050. Min Act: -0.1697
Data Index: 3844727 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.7738. Min Act: -0.1700
Data Index: 5724746 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8363. Min Act: -0.1699
Data Index: 782024 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8675. Min Act: -0.1700
Data Index: 7492373 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8050. Min Act: -0.1700
Data Index: 7392626 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.7738. Min Act: -0.1700
Data Index: 7664676 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.7113. Min Act: -0.1700
Data Index: 5107704 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.7425. Min Act: -0.1700
Data Index: 382275 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.7425. Min Act: -0.1700
Data Index: 2211037 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.7425. Min Act: -0.1700
Data Index: 1621926 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8050. Min Act: -0.1698
Data Index: 1712211 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.7425. Min Act: -0.1700
Data Index: 7738822 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9613. Min Range: -4.9613
Max Act: 4.8050. Min Act: -0.1700
Data Index: 2041404 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19