Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6365 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.8264. Min Act: -0.1700
Data Index: 7201147 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.6077. Min Act: -0.1700
Data Index: 5027342 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.6077. Min Act: -0.1700
Data Index: 3284072 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.6077. Min Act: -0.1700
Data Index: 8331440 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.6389. Min Act: -0.1700
Data Index: 7201154 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.4827. Min Act: -0.1700
Data Index: 2501133 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.4827. Min Act: -0.1700
Data Index: 2606915 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.3577. Min Act: -0.1700
Data Index: 2553122 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.3264. Min Act: -0.1700
Data Index: 5049543 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.3264. Min Act: -0.1700
Data Index: 7446211 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.2952. Min Act: -0.1700
Data Index: 8549301 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.3264. Min Act: -0.1700
Data Index: 2270014 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.2014. Min Act: -0.1700
Data Index: 5102461 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.2014. Min Act: -0.1700
Data Index: 854440 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.2014. Min Act: -0.1700
Data Index: 2906093 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.2014. Min Act: -0.1700
Data Index: 6873217 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.1702. Min Act: -0.1700
Data Index: 7381669 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.1702. Min Act: -0.1700
Data Index: 7693243 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.1389. Min Act: -0.1700
Data Index: 2332268 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8264. Min Range: -5.8264
Max Act: 5.1389. Min Act: -0.1700
Data Index: 4708403 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19