Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2416 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0800. Min Range: -5.0800
Max Act: 5.0800. Min Act: -0.1700
Data Index: 7347707 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0800. Min Range: -5.0800
Max Act: 5.0800. Min Act: -0.1700
Data Index: 8503132 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.9550. Min Act: -0.1700
Data Index: 6128468 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.9550. Min Act: -0.1700
Data Index: 6477757 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.8925. Min Act: -0.1700
Data Index: 4712978 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7987. Min Act: -0.1700
Data Index: 5123168 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7987. Min Act: -0.1700
Data Index: 6686399 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7987. Min Act: -0.1700
Data Index: 4024205 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7050. Min Act: -0.1700
Data Index: 4772166 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7362. Min Act: -0.1700
Data Index: 7979171 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7362. Min Act: -0.1700
Data Index: 489697 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7362. Min Act: -0.1700
Data Index: 548907 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7362. Min Act: -0.1700
Data Index: 3555649 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7050. Min Act: -0.1700
Data Index: 2863507 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7362. Min Act: -0.1700
Data Index: 1692588 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7050. Min Act: -0.1700
Data Index: 7118835 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7050. Min Act: -0.1700
Data Index: 597628 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7050. Min Act: -0.1700
Data Index: 7771517 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.6737. Min Act: -0.1700
Data Index: 2832050 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0800. Min Range: -5.0800
Max Act: 4.7050. Min Act: -0.1700
Data Index: 662881 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19