Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1552 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.3387. Min Act: -0.1700
Data Index: 2450388 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.3387. Min Act: -0.1700
Data Index: 1909764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.3211. Min Act: -0.1684
Data Index: 2174500 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2946. Min Act: -0.1700
Data Index: 7756839 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.3035. Min Act: -0.1700
Data Index: 994427 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2858. Min Act: -0.1699
Data Index: 2874520 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2946. Min Act: -0.1699
Data Index: 7468773 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2946. Min Act: -0.1694
Data Index: 8474039 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2858. Min Act: -0.1699
Data Index: 7769921 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2770. Min Act: -0.1699
Data Index: 3602096 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2770. Min Act: -0.1690
Data Index: 4800258 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2858. Min Act: -0.1700
Data Index: 6384572 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2682. Min Act: -0.1698
Data Index: 7254707 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2682. Min Act: -0.1700
Data Index: 2502697 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2594. Min Act: -0.1700
Data Index: 7106915 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2682. Min Act: -0.1700
Data Index: 5494377 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2594. Min Act: -0.1698
Data Index: 2045016 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2770. Min Act: -0.1698
Data Index: 1909765 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2594. Min Act: -0.1700
Data Index: 2865082 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2594. Min Act: -0.1700
Data Index: 7639497 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19