Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2226 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5777. Min Range: -8.5777
Max Act: 8.5777. Min Act: -0.1700
Data Index: 3033328 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5777. Min Range: -8.5777
Max Act: 8.2652. Min Act: -0.1700
Data Index: 172690 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5777. Min Range: -8.5777
Max Act: 8.1402. Min Act: -0.1700
Data Index: 8510570 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5777. Min Range: -8.5777
Max Act: 8.0777. Min Act: -0.1700
Data Index: 7439982 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5777. Min Range: -8.5777
Max Act: 8.0777. Min Act: -0.1700
Data Index: 4782900 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.8902. Min Act: -0.1700
Data Index: 4941090 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.9527. Min Act: -0.1700
Data Index: 7043591 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.8902. Min Act: -0.1700
Data Index: 4998908 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.8902. Min Act: -0.1700
Data Index: 3724592 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.8277. Min Act: -0.1700
Data Index: 1518721 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.8902. Min Act: -0.1700
Data Index: 7633142 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.8277. Min Act: -0.1700
Data Index: 7817137 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.8277. Min Act: -0.1700
Data Index: 3012295 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.8277. Min Act: -0.1700
Data Index: 3899793 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.7652. Min Act: -0.1700
Data Index: 443818 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.7652. Min Act: -0.1700
Data Index: 4557004 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.6714. Min Act: -0.1700
Data Index: 4649767 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.7027. Min Act: -0.1700
Data Index: 1918323 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.7027. Min Act: -0.1700
Data Index: 8726790 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5777. Min Range: -8.5777
Max Act: 7.6714. Min Act: -0.1700
Data Index: 4283388 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19