Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4109 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1674. Min Range: -8.1674
Max Act: 8.1674. Min Act: -0.1700
Data Index: 588947 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1674. Min Range: -8.1674
Max Act: 8.1049. Min Act: -0.1700
Data Index: 4475038 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1674. Min Range: -8.1674
Max Act: 8.0111. Min Act: -0.1700
Data Index: 4575597 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.9799. Min Act: -0.1700
Data Index: 8116681 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.9174. Min Act: -0.1700
Data Index: 822138 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.9486. Min Act: -0.1700
Data Index: 3532638 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.8861. Min Act: -0.1700
Data Index: 8367269 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.7299. Min Act: -0.1700
Data Index: 6501928 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.6674. Min Act: -0.1700
Data Index: 631765 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.6674. Min Act: -0.1700
Data Index: 2355847 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.6674. Min Act: -0.1700
Data Index: 1349447 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.6361. Min Act: -0.1700
Data Index: 846592 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.6361. Min Act: -0.1700
Data Index: 851070 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.6049. Min Act: -0.1700
Data Index: 6384100 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.6049. Min Act: -0.1700
Data Index: 6705643 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.5424. Min Act: -0.1700
Data Index: 6419594 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.5424. Min Act: -0.1700
Data Index: 8465948 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.5111. Min Act: -0.1700
Data Index: 5546173 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.4799. Min Act: -0.1700
Data Index: 3001165 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1674. Min Range: -8.1674
Max Act: 7.5111. Min Act: -0.1700
Data Index: 3067382 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19