Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.6548. Min Act: -0.1700
Data Index: 3910803 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.6227. Min Act: -0.1700
Data Index: 3910802 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.6066. Min Act: -0.1700
Data Index: 6446644 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.6066. Min Act: -0.1700
Data Index: 364638 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5744. Min Act: -0.1700
Data Index: 6428937 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5744. Min Act: -0.1700
Data Index: 1386797 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5744. Min Act: -0.1700
Data Index: 2192990 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5583. Min Act: -0.1700
Data Index: 6724020 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5583. Min Act: -0.1700
Data Index: 6384493 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5422. Min Act: -0.1700
Data Index: 5010879 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5422. Min Act: -0.1700
Data Index: 2225576 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5260. Min Act: -0.1700
Data Index: 3281355 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5422. Min Act: -0.1700
Data Index: 1634039 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5422. Min Act: -0.1700
Data Index: 3457923 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5422. Min Act: -0.1700
Data Index: 5724454 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5260. Min Act: -0.1700
Data Index: 210785 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5098. Min Act: -0.1700
Data Index: 668787 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5260. Min Act: -0.1700
Data Index: 6553287 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5098. Min Act: -0.1700
Data Index: 2172688 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6548. Min Range: -2.6548
Max Act: 2.5422. Min Act: -0.1700
Data Index: 2083580 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19