Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.4952. Min Act: -0.1700
Data Index: 8684381 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.3702. Min Act: -0.1700
Data Index: 2800366 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.2765. Min Act: -0.1700
Data Index: 8147956 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.2452. Min Act: -0.1700
Data Index: 1248033 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.1827. Min Act: -0.1700
Data Index: 339447 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.1515. Min Act: -0.1700
Data Index: 7904429 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.1202. Min Act: -0.1700
Data Index: 8246309 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.0890. Min Act: -0.1700
Data Index: 3521918 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4952. Min Range: -6.4952
Max Act: 6.0265. Min Act: -0.1700
Data Index: 7878835 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9640. Min Act: -0.1700
Data Index: 4175558 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9952. Min Act: -0.1700
Data Index: 109055 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9640. Min Act: -0.1700
Data Index: 7952807 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9327. Min Act: -0.1700
Data Index: 2324686 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9640. Min Act: -0.1700
Data Index: 547273 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9327. Min Act: -0.1700
Data Index: 877899 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9327. Min Act: -0.1700
Data Index: 4496723 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9015. Min Act: -0.1700
Data Index: 3195610 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9327. Min Act: -0.1700
Data Index: 1885155 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.9327. Min Act: -0.1700
Data Index: 2914874 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4952. Min Range: -6.4952
Max Act: 5.8390. Min Act: -0.1700
Data Index: 1283664 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19