Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4027 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.7716. Min Act: -0.1700
Data Index: 401525 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.6621. Min Act: -0.1700
Data Index: 6333752 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.5369. Min Act: -0.1700
Data Index: 4469614 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.4899. Min Act: -0.1700
Data Index: 4224707 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.4273. Min Act: -0.1700
Data Index: 3091066 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.4429. Min Act: -0.1700
Data Index: 7074785 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3959. Min Act: -0.1700
Data Index: 3498222 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.4116. Min Act: -0.1700
Data Index: 4135001 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3959. Min Act: -0.1700
Data Index: 5811372 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3959. Min Act: -0.1700
Data Index: 3370814 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3645. Min Act: -0.1700
Data Index: 3384348 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3802. Min Act: -0.1700
Data Index: 4941746 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3645. Min Act: -0.1700
Data Index: 516209 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3802. Min Act: -0.1700
Data Index: 3794025 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3959. Min Act: -0.1700
Data Index: 3289493 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3802. Min Act: -0.1700
Data Index: 5921051 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3802. Min Act: -0.1700
Data Index: 3860106 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3802. Min Act: -0.1700
Data Index: 2773021 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3645. Min Act: -0.1700
Data Index: 540791 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7716. Min Range: -3.7716
Max Act: 3.3645. Min Act: -0.1700
Data Index: 6289788 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19