Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.8919. Min Act: -0.1700
Data Index: 120359 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.8606. Min Act: -0.1700
Data Index: 8770280 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.8294. Min Act: -0.1700
Data Index: 6797005 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7669. Min Act: -0.1700
Data Index: 6343098 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7669. Min Act: -0.1700
Data Index: 3045936 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7356. Min Act: -0.1700
Data Index: 2794914 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7356. Min Act: -0.1700
Data Index: 2505317 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7356. Min Act: -0.1700
Data Index: 8796539 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7669. Min Act: -0.1700
Data Index: 718866 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 3736688 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 8381143 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 6596905 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 769349 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 6423712 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7356. Min Act: -0.1700
Data Index: 5846775 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 2517029 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 582721 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 4799004 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.6731. Min Act: -0.1700
Data Index: 326256 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8919. Min Range: -5.8919
Max Act: 5.7044. Min Act: -0.1700
Data Index: 2462523 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19