Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.5568. Min Act: -0.1700
Data Index: 16615 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.5256. Min Act: -0.1700
Data Index: 4654533 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.4943. Min Act: -0.1700
Data Index: 490473 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.4631. Min Act: -0.1700
Data Index: 3070378 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.4631. Min Act: -0.1700
Data Index: 5863102 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.4318. Min Act: -0.1700
Data Index: 3121219 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.3693. Min Act: -0.1700
Data Index: 7946536 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.3068. Min Act: -0.1700
Data Index: 2242956 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.3068. Min Act: -0.1700
Data Index: 3366747 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.3381. Min Act: -0.1700
Data Index: 6695546 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.3068. Min Act: -0.1700
Data Index: 8280367 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.3068. Min Act: -0.1700
Data Index: 1545550 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.3068. Min Act: -0.1700
Data Index: 4669908 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.2756. Min Act: -0.1700
Data Index: 8428628 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.2756. Min Act: -0.1700
Data Index: 2752562 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.2756. Min Act: -0.1700
Data Index: 2592505 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.2756. Min Act: -0.1700
Data Index: 792408 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.3068. Min Act: -0.1700
Data Index: 6507649 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.2443. Min Act: -0.1700
Data Index: 3026099 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5568. Min Range: -4.5568
Max Act: 4.2443. Min Act: -0.1700
Data Index: 1339539 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19