Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.3241. Min Act: -0.1700
Data Index: 8586649 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2747. Min Act: -0.1700
Data Index: 366332 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2582. Min Act: -0.1700
Data Index: 1721331 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2582. Min Act: -0.1700
Data Index: 6585122 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2582. Min Act: -0.1700
Data Index: 7771194 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2582. Min Act: -0.1700
Data Index: 1429910 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2582. Min Act: -0.1700
Data Index: 736069 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2251. Min Act: -0.1700
Data Index: 8551935 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2417. Min Act: -0.1700
Data Index: 7554418 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2086. Min Act: -0.1700
Data Index: 5268925 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2251. Min Act: -0.1700
Data Index: 4733539 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2251. Min Act: -0.1700
Data Index: 2336762 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2086. Min Act: -0.1700
Data Index: 764493 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.2251. Min Act: -0.1700
Data Index: 7151997 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.1920. Min Act: -0.1700
Data Index: 3128669 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.1920. Min Act: -0.1700
Data Index: 1410891 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.1920. Min Act: -0.1700
Data Index: 7885519 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.1920. Min Act: -0.1700
Data Index: 4607021 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.1754. Min Act: -0.1700
Data Index: 5633796 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3241. Min Range: -2.3241
Max Act: 2.1754. Min Act: -0.1700
Data Index: 2656762 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19