Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.1829. Min Act: -0.1700
Data Index: 8125898 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.1672. Min Act: -0.1700
Data Index: 3641096 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.1672. Min Act: -0.1700
Data Index: 1961838 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.1357. Min Act: -0.1700
Data Index: 4058904 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.1200. Min Act: -0.1700
Data Index: 7919041 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.1200. Min Act: -0.1700
Data Index: 2903491 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.1042. Min Act: -0.1700
Data Index: 7207912 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.1042. Min Act: -0.1700
Data Index: 4573036 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0727. Min Act: -0.1700
Data Index: 5157389 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0411. Min Act: -0.1700
Data Index: 2906355 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0253. Min Act: -0.1700
Data Index: 5296686 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0253. Min Act: -0.1700
Data Index: 4794212 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0411. Min Act: -0.1700
Data Index: 7917712 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0253. Min Act: -0.1700
Data Index: 367049 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0095. Min Act: -0.1700
Data Index: 7007932 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0095. Min Act: -0.1700
Data Index: 3084670 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1829. Min Range: -3.1829
Max Act: 3.0095. Min Act: -0.1700
Data Index: 2752850 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1829. Min Range: -3.1829
Max Act: 2.9937. Min Act: -0.1700
Data Index: 4237219 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1829. Min Range: -3.1829
Max Act: 2.9937. Min Act: -0.1700
Data Index: 2852296 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1829. Min Range: -3.1829
Max Act: 2.9937. Min Act: -0.1700
Data Index: 1771188 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19