Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.5572. Min Act: -0.1700
Data Index: 1347238 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.5259. Min Act: -0.1700
Data Index: 831084 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.4947. Min Act: -0.1700
Data Index: 384714 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.4634. Min Act: -0.1700
Data Index: 7447727 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.4322. Min Act: -0.1700
Data Index: 5798202 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.4322. Min Act: -0.1700
Data Index: 1787739 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.4009. Min Act: -0.1700
Data Index: 168075 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3697. Min Act: -0.1700
Data Index: 1894886 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3697. Min Act: -0.1700
Data Index: 1347214 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3697. Min Act: -0.1700
Data Index: 1915481 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3697. Min Act: -0.1700
Data Index: 6135806 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3697. Min Act: -0.1700
Data Index: 6135810 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3384. Min Act: -0.1700
Data Index: 8587784 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3384. Min Act: -0.1700
Data Index: 6683507 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3072. Min Act: -0.1700
Data Index: 1655353 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3072. Min Act: -0.1700
Data Index: 7787434 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3072. Min Act: -0.1700
Data Index: 3750637 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3072. Min Act: -0.1700
Data Index: 949579 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.3072. Min Act: -0.1700
Data Index: 3255348 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5572. Min Range: -5.5572
Max Act: 5.2447. Min Act: -0.1700
Data Index: 3384919 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19