Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3729. Min Range: -5.3729
Max Act: 5.3729. Min Act: -0.1700
Data Index: 5711698 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9979. Min Act: -0.1700
Data Index: 2376426 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9666. Min Act: -0.1700
Data Index: 4221423 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9354. Min Act: -0.1700
Data Index: 2695527 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9354. Min Act: -0.1700
Data Index: 6049050 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9354. Min Act: -0.1700
Data Index: 1230466 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9354. Min Act: -0.1700
Data Index: 5278363 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9041. Min Act: -0.1700
Data Index: 16710 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9041. Min Act: -0.1700
Data Index: 2849307 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9041. Min Act: -0.1700
Data Index: 4165785 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.8729. Min Act: -0.1700
Data Index: 16708 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.9041. Min Act: -0.1700
Data Index: 7013529 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.8416. Min Act: -0.1700
Data Index: 5289204 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.8416. Min Act: -0.1700
Data Index: 714960 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.8416. Min Act: -0.1700
Data Index: 702841 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.8416. Min Act: -0.1700
Data Index: 764204 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.8104. Min Act: -0.1700
Data Index: 1648165 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.7791. Min Act: -0.1700
Data Index: 8617841 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.8104. Min Act: -0.1700
Data Index: 8323115 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3729. Min Range: -5.3729
Max Act: 4.8104. Min Act: -0.1700
Data Index: 2407583 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19