Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3715 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.9062. Min Act: -0.1700
Data Index: 7521551 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.8750. Min Act: -0.1700
Data Index: 7627821 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.7812. Min Act: -0.1700
Data Index: 365459 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.6250. Min Act: -0.1700
Data Index: 3896628 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.6562. Min Act: -0.1700
Data Index: 7427453 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.5937. Min Act: -0.1700
Data Index: 2883441 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.5937. Min Act: -0.1700
Data Index: 5712445 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.5625. Min Act: -0.1700
Data Index: 6703664 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.5312. Min Act: -0.1700
Data Index: 2909727 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.5625. Min Act: -0.1700
Data Index: 632972 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.5000. Min Act: -0.1700
Data Index: 438315 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.5000. Min Act: -0.1700
Data Index: 4681358 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7939217 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.4687. Min Act: -0.1700
Data Index: 5758837 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.4687. Min Act: -0.1700
Data Index: 5062003 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.4687. Min Act: -0.1700
Data Index: 7794968 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.4375. Min Act: -0.1700
Data Index: 5776399 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.4375. Min Act: -0.1700
Data Index: 159577 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.4062. Min Act: -0.1700
Data Index: 1638914 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9062. Min Range: -5.9062
Max Act: 5.4375. Min Act: -0.1700
Data Index: 1740428 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19