Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5068 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.3941. Min Act: -0.1700
Data Index: 2069123 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.3628. Min Act: -0.1700
Data Index: 7383147 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.0503. Min Act: -0.1700
Data Index: 278313 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.0503. Min Act: -0.1700
Data Index: 76330 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.0191. Min Act: -0.1700
Data Index: 278301 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.9253. Min Act: -0.1700
Data Index: 2106275 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8628. Min Act: -0.1700
Data Index: 2747063 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8316. Min Act: -0.1700
Data Index: 2235068 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8316. Min Act: -0.1700
Data Index: 5479166 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8316. Min Act: -0.1700
Data Index: 3190820 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8003. Min Act: -0.1700
Data Index: 1761769 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8003. Min Act: -0.1700
Data Index: 2634759 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.7691. Min Act: -0.1700
Data Index: 2353216 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.7691. Min Act: -0.1700
Data Index: 3373521 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.7691. Min Act: -0.1700
Data Index: 6754804 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.7691. Min Act: -0.1700
Data Index: 6652173 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.7691. Min Act: -0.1700
Data Index: 74400 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.7378. Min Act: -0.1700
Data Index: 7239825 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.7378. Min Act: -0.1700
Data Index: 3436140 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.7066. Min Act: -0.1700
Data Index: 1608540 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19