Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2520 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.6185. Min Act: -0.1700
Data Index: 6320704 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.6185. Min Act: -0.1700
Data Index: 7476421 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.4935. Min Act: -0.1700
Data Index: 1041267 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.4310. Min Act: -0.1700
Data Index: 4347071 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.3998. Min Act: -0.1700
Data Index: 8483431 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.3373. Min Act: -0.1700
Data Index: 6006687 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.3060. Min Act: -0.1700
Data Index: 4828645 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.3060. Min Act: -0.1700
Data Index: 6475003 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.3060. Min Act: -0.1700
Data Index: 2097693 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.2748. Min Act: -0.1700
Data Index: 4257382 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.2123. Min Act: -0.1700
Data Index: 6779877 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.2435. Min Act: -0.1700
Data Index: 7413727 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.2123. Min Act: -0.1700
Data Index: 6953873 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.1810. Min Act: -0.1700
Data Index: 1257775 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.1810. Min Act: -0.1700
Data Index: 1557086 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.1498. Min Act: -0.1700
Data Index: 5726274 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.1810. Min Act: -0.1700
Data Index: 5021613 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.1498. Min Act: -0.1700
Data Index: 6947474 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.1185. Min Act: -0.1700
Data Index: 792611 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6185. Min Range: -6.6185
Max Act: 6.1498. Min Act: -0.1700
Data Index: 2207028 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19