Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5439 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.9679. Min Act: -0.1700
Data Index: 697499 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.6241. Min Act: -0.1700
Data Index: 6112616 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.5616. Min Act: -0.1700
Data Index: 4731376 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.4679. Min Act: -0.1700
Data Index: 6112617 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.4054. Min Act: -0.1700
Data Index: 376186 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.3741. Min Act: -0.1700
Data Index: 1221723 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.3429. Min Act: -0.1700
Data Index: 2304017 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.3429. Min Act: -0.1700
Data Index: 901422 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.3116. Min Act: -0.1700
Data Index: 712194 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2804. Min Act: -0.1700
Data Index: 8382732 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2491. Min Act: -0.1700
Data Index: 2020899 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2179. Min Act: -0.1700
Data Index: 3309880 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2179. Min Act: -0.1700
Data Index: 3184094 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2179. Min Act: -0.1700
Data Index: 5844323 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2179. Min Act: -0.1700
Data Index: 785769 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2179. Min Act: -0.1700
Data Index: 5427496 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2179. Min Act: -0.1700
Data Index: 5582622 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.2179. Min Act: -0.1700
Data Index: 4638553 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.1866. Min Act: -0.1700
Data Index: 5570116 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9679. Min Range: -5.9679
Max Act: 5.1866. Min Act: -0.1700
Data Index: 1172282 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19