Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4346. Min Range: -4.4346
Max Act: 4.4346. Min Act: -0.1700
Data Index: 2957666 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4346. Min Range: -4.4346
Max Act: 4.3721. Min Act: -0.1700
Data Index: 961930 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4346. Min Range: -4.4346
Max Act: 4.0283. Min Act: -0.1700
Data Index: 1260054 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.9345. Min Act: -0.1700
Data Index: 1260055 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.8407. Min Act: -0.1700
Data Index: 4191835 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.7782. Min Act: -0.1700
Data Index: 5460556 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.7625. Min Act: -0.1700
Data Index: 1260057 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.7156. Min Act: -0.1700
Data Index: 5615366 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.6687. Min Act: -0.1700
Data Index: 2789022 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.6687. Min Act: -0.1700
Data Index: 109175 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.6687. Min Act: -0.1700
Data Index: 1260053 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.5591. Min Act: -0.1700
Data Index: 1260056 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.5435. Min Act: -0.1700
Data Index: 2378902 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.5591. Min Act: -0.1700
Data Index: 2464984 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.5122. Min Act: -0.1700
Data Index: 8828888 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.5122. Min Act: -0.1700
Data Index: 7001536 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.4652. Min Act: -0.1700
Data Index: 2544813 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.4495. Min Act: -0.1700
Data Index: 2782179 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.4495. Min Act: -0.1700
Data Index: 3305600 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4346. Min Range: -4.4346
Max Act: 3.4495. Min Act: -0.1700
Data Index: 2544812 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19