Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4786 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.9090. Min Act: -0.1700
Data Index: 8508240 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.9403. Min Act: -0.1700
Data Index: 5005395 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.9090. Min Act: -0.1700
Data Index: 658749 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8465. Min Act: -0.1700
Data Index: 2385429 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8778. Min Act: -0.1700
Data Index: 2022535 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8778. Min Act: -0.1700
Data Index: 5568043 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8465. Min Act: -0.1700
Data Index: 4693636 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8153. Min Act: -0.1700
Data Index: 7535078 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.7840. Min Act: -0.1700
Data Index: 3519514 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8465. Min Act: -0.1700
Data Index: 8340411 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8153. Min Act: -0.1700
Data Index: 4154674 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8153. Min Act: -0.1700
Data Index: 1912409 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.7840. Min Act: -0.1700
Data Index: 4845485 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.7840. Min Act: -0.1700
Data Index: 783944 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.8153. Min Act: -0.1700
Data Index: 6021688 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.7840. Min Act: -0.1700
Data Index: 2897894 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.7840. Min Act: -0.1700
Data Index: 4146966 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.7840. Min Act: -0.1700
Data Index: 5441331 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.7528. Min Act: -0.1700
Data Index: 3410924 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9403. Min Range: -4.9403
Max Act: 4.7528. Min Act: -0.1700
Data Index: 3738191 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19