Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.3127. Min Act: -0.1700
Data Index: 8566963 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.2814. Min Act: -0.1700
Data Index: 2591800 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.2189. Min Act: -0.1700
Data Index: 3001880 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.2189. Min Act: -0.1700
Data Index: 2040003 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.1877. Min Act: -0.1700
Data Index: 978020 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.1252. Min Act: -0.1700
Data Index: 1825085 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.1252. Min Act: -0.1700
Data Index: 4318477 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.1252. Min Act: -0.1700
Data Index: 2354456 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.0939. Min Act: -0.1700
Data Index: 6548455 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.0314. Min Act: -0.1700
Data Index: 5791063 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.0627. Min Act: -0.1700
Data Index: 2534733 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.0002. Min Act: -0.1700
Data Index: 3001878 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.0002. Min Act: -0.1700
Data Index: 765003 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.0002. Min Act: -0.1700
Data Index: 3494033 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.0002. Min Act: -0.1700
Data Index: 8633029 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3127. Min Range: -5.3127
Max Act: 5.0002. Min Act: -0.1700
Data Index: 5245239 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3127. Min Range: -5.3127
Max Act: 4.9689. Min Act: -0.1700
Data Index: 6405550 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3127. Min Range: -5.3127
Max Act: 4.9689. Min Act: -0.1700
Data Index: 4765124 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3127. Min Range: -5.3127
Max Act: 4.9377. Min Act: -0.1700
Data Index: 7020132 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3127. Min Range: -5.3127
Max Act: 4.9377. Min Act: -0.1700
Data Index: 4626830 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19