Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 430 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.8898. Min Act: -0.1700
Data Index: 6304408 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.6710. Min Act: -0.1700
Data Index: 7060490 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.6085. Min Act: -0.1700
Data Index: 7955425 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.5148. Min Act: -0.1700
Data Index: 344223 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.5460. Min Act: -0.1700
Data Index: 448007 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.5148. Min Act: -0.1700
Data Index: 1336494 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.4523. Min Act: -0.1700
Data Index: 8631507 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.4523. Min Act: -0.1700
Data Index: 184881 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.4210. Min Act: -0.1700
Data Index: 5206847 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3898. Min Act: -0.1700
Data Index: 4381609 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3898. Min Act: -0.1700
Data Index: 1430929 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3898. Min Act: -0.1700
Data Index: 3405422 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3898. Min Act: -0.1700
Data Index: 1263471 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3898. Min Act: -0.1700
Data Index: 2002592 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3585. Min Act: -0.1700
Data Index: 4411766 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3585. Min Act: -0.1700
Data Index: 6125198 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3585. Min Act: -0.1700
Data Index: 213221 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3585. Min Act: -0.1700
Data Index: 344233 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3585. Min Act: -0.1700
Data Index: 4658075 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3585. Min Act: -0.1700
Data Index: 5025963 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19