Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1449 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5945. Min Range: -9.5945
Max Act: 9.5945. Min Act: -0.1700
Data Index: 1470135 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5945. Min Range: -9.5945
Max Act: 9.4695. Min Act: -0.1700
Data Index: 34230 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5945. Min Range: -9.5945
Max Act: 9.4070. Min Act: -0.1700
Data Index: 3816928 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5945. Min Range: -9.5945
Max Act: 9.1570. Min Act: -0.1700
Data Index: 773173 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5945. Min Range: -9.5945
Max Act: 9.1570. Min Act: -0.1700
Data Index: 8422638 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5945. Min Range: -9.5945
Max Act: 9.1570. Min Act: -0.1700
Data Index: 34231 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5945. Min Range: -9.5945
Max Act: 9.0320. Min Act: -0.1700
Data Index: 2689843 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5945. Min Range: -9.5945
Max Act: 9.0320. Min Act: -0.1700
Data Index: 4355966 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.9070. Min Act: -0.1700
Data Index: 3816925 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.9695. Min Act: -0.1700
Data Index: 7286416 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.9695. Min Act: -0.1700
Data Index: 5948129 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.9070. Min Act: -0.1700
Data Index: 2175286 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.9070. Min Act: -0.1700
Data Index: 8262388 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.9070. Min Act: -0.1700
Data Index: 2014201 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.8445. Min Act: -0.1700
Data Index: 3224865 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.8445. Min Act: -0.1700
Data Index: 5336171 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.8445. Min Act: -0.1700
Data Index: 1656403 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.8445. Min Act: -0.1700
Data Index: 6262506 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.7820. Min Act: -0.1700
Data Index: 2355976 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5945. Min Range: -9.5945
Max Act: 8.7820. Min Act: -0.1700
Data Index: 688914 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19