Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.5931. Min Act: -0.1700
Data Index: 3872331 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.5619. Min Act: -0.1700
Data Index: 2568387 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.5619. Min Act: -0.1700
Data Index: 5397628 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.5619. Min Act: -0.1700
Data Index: 8439528 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.5306. Min Act: -0.1700
Data Index: 4064301 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4994. Min Act: -0.1700
Data Index: 697777 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4994. Min Act: -0.1700
Data Index: 1751532 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.5306. Min Act: -0.1700
Data Index: 3432790 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4681. Min Act: -0.1700
Data Index: 2747832 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4369. Min Act: -0.1700
Data Index: 5844564 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4369. Min Act: -0.1700
Data Index: 493502 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4369. Min Act: -0.1700
Data Index: 3899570 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4056. Min Act: -0.1700
Data Index: 8330356 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4056. Min Act: -0.1700
Data Index: 5767757 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4056. Min Act: -0.1700
Data Index: 2508157 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.4056. Min Act: -0.1700
Data Index: 7484069 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.3744. Min Act: -0.1700
Data Index: 3917443 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.3744. Min Act: -0.1700
Data Index: 3589910 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.3431. Min Act: -0.1700
Data Index: 744589 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.3431. Min Act: -0.1700
Data Index: 5626427 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19