Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5112 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1931. Min Range: -8.1931
Max Act: 8.1931. Min Act: -0.1700
Data Index: 4305521 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.8806. Min Act: -0.1700
Data Index: 600461 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.8806. Min Act: -0.1700
Data Index: 1145186 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.8181. Min Act: -0.1700
Data Index: 5428895 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.8181. Min Act: -0.1700
Data Index: 555616 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.8181. Min Act: -0.1700
Data Index: 3962356 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.8181. Min Act: -0.1700
Data Index: 8588372 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.7556. Min Act: -0.1700
Data Index: 8359496 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6931. Min Act: -0.1700
Data Index: 8044602 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6931. Min Act: -0.1700
Data Index: 2648031 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6306. Min Act: -0.1700
Data Index: 4934109 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6931. Min Act: -0.1700
Data Index: 6058689 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6931. Min Act: -0.1700
Data Index: 5687903 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6931. Min Act: -0.1700
Data Index: 1668691 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6931. Min Act: -0.1700
Data Index: 3698069 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6306. Min Act: -0.1700
Data Index: 4442474 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6306. Min Act: -0.1700
Data Index: 6900258 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6306. Min Act: -0.1700
Data Index: 5939304 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6306. Min Act: -0.1700
Data Index: 3601623 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1931. Min Range: -8.1931
Max Act: 7.6306. Min Act: -0.1700
Data Index: 6827085 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19