Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.5674. Min Act: -0.1700
Data Index: 3347075 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.5049. Min Act: -0.1700
Data Index: 6478527 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.5049. Min Act: -0.1700
Data Index: 6010883 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4737. Min Act: -0.1700
Data Index: 3909507 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4737. Min Act: -0.1700
Data Index: 1641026 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4424. Min Act: -0.1700
Data Index: 3894266 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4424. Min Act: -0.1700
Data Index: 4613521 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4424. Min Act: -0.1700
Data Index: 6105927 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4112. Min Act: -0.1700
Data Index: 5495750 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4112. Min Act: -0.1700
Data Index: 3443578 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3799. Min Act: -0.1700
Data Index: 6141993 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3799. Min Act: -0.1700
Data Index: 1846179 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3799. Min Act: -0.1700
Data Index: 601522 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3487. Min Act: -0.1700
Data Index: 3458505 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.2862. Min Act: -0.1700
Data Index: 8295881 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3174. Min Act: -0.1700
Data Index: 5627000 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.2862. Min Act: -0.1700
Data Index: 4231462 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.2862. Min Act: -0.1700
Data Index: 1181561 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.2862. Min Act: -0.1700
Data Index: 4526762 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.2862. Min Act: -0.1700
Data Index: 1868461 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19