Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.6966. Min Act: -0.1700
Data Index: 3544663 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.6341. Min Act: -0.1700
Data Index: 7808474 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.6028. Min Act: -0.1700
Data Index: 782583 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.6028. Min Act: -0.1700
Data Index: 6819776 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.6028. Min Act: -0.1700
Data Index: 544851 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5716. Min Act: -0.1700
Data Index: 1756855 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.6028. Min Act: -0.1700
Data Index: 3456427 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5716. Min Act: -0.1700
Data Index: 1303888 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5716. Min Act: -0.1700
Data Index: 3006182 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5716. Min Act: -0.1700
Data Index: 5079880 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5403. Min Act: -0.1700
Data Index: 1336451 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5091. Min Act: -0.1700
Data Index: 8646780 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5403. Min Act: -0.1700
Data Index: 7725787 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5403. Min Act: -0.1700
Data Index: 3873132 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5403. Min Act: -0.1700
Data Index: 421060 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5403. Min Act: -0.1700
Data Index: 139844 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5403. Min Act: -0.1700
Data Index: 4608727 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5091. Min Act: -0.1700
Data Index: 988061 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5091. Min Act: -0.1700
Data Index: 6899538 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5091. Min Act: -0.1700
Data Index: 4355677 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19