Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 651 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4321. Min Act: -0.1700
Data Index: 3967475 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4009. Min Act: -0.1700
Data Index: 5652202 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4009. Min Act: -0.1700
Data Index: 7606289 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4009. Min Act: -0.1700
Data Index: 6540993 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4009. Min Act: -0.1700
Data Index: 5897588 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4009. Min Act: -0.1700
Data Index: 3087876 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4321. Min Act: -0.1700
Data Index: 4616303 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4009. Min Act: -0.1700
Data Index: 416720 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 8503273 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 1658386 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 1554348 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 4897457 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 4365296 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 5774849 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 646948 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 2151790 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 4265961 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 7174105 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 7200522 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 7596555 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19