Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4558 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.3931. Min Act: -0.1700
Data Index: 3933462 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.2056. Min Act: -0.1699
Data Index: 8728319 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9556. Min Act: -0.1700
Data Index: 4445717 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9556. Min Act: -0.1700
Data Index: 4333107 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9556. Min Act: -0.1700
Data Index: 7781049 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9243. Min Act: -0.1700
Data Index: 6269439 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9243. Min Act: -0.1700
Data Index: 4564911 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.8931. Min Act: -0.1700
Data Index: 7779906 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7993. Min Act: -0.1700
Data Index: 4332042 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7993. Min Act: -0.1700
Data Index: 3630277 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.8306. Min Act: -0.1700
Data Index: 3533056 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7993. Min Act: -0.1700
Data Index: 8693621 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7681. Min Act: -0.1700
Data Index: 4346846 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7681. Min Act: -0.1700
Data Index: 796724 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7681. Min Act: -0.1700
Data Index: 6472450 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7368. Min Act: -0.1700
Data Index: 1865611 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7056. Min Act: -0.1700
Data Index: 2950505 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7056. Min Act: -0.1700
Data Index: 4250849 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7056. Min Act: -0.1700
Data Index: 4972371 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.7056. Min Act: -0.1700
Data Index: 6751548 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19