Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5214 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0827. Min Range: -4.0827
Max Act: 4.0827. Min Act: -0.1700
Data Index: 1515543 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0827. Min Range: -4.0827
Max Act: 4.0515. Min Act: -0.1700
Data Index: 4276716 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0827. Min Range: -4.0827
Max Act: 4.0202. Min Act: -0.1700
Data Index: 4193352 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0827. Min Range: -4.0827
Max Act: 4.0202. Min Act: -0.1700
Data Index: 5139517 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9889. Min Act: -0.1700
Data Index: 485389 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0827. Min Range: -4.0827
Max Act: 4.0202. Min Act: -0.1700
Data Index: 1628228 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9889. Min Act: -0.1700
Data Index: 966558 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9889. Min Act: -0.1700
Data Index: 6732813 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 1036174 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 8000405 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 3100284 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 2952432 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9889. Min Act: -0.1700
Data Index: 87049 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 2763099 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9264. Min Act: -0.1700
Data Index: 7751543 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 7380309 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 618326 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 6625417 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 4850755 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 715850 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19