Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4229 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.4202. Min Act: -0.1700
Data Index: 3621663 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.4202. Min Act: -0.1700
Data Index: 1368802 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 980221 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3265. Min Act: -0.1700
Data Index: 404500 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2952. Min Act: -0.1700
Data Index: 4296179 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 3855460 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2640. Min Act: -0.1700
Data Index: 7691808 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 6657580 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 3494435 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2015. Min Act: -0.1700
Data Index: 7973280 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 5533892 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 8571218 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 3530274 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 5963770 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 5071831 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1390. Min Act: -0.1700
Data Index: 8488425 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1390. Min Act: -0.1700
Data Index: 8665777 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1077. Min Act: -0.1700
Data Index: 3780061 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1077. Min Act: -0.1700
Data Index: 621229 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1390. Min Act: -0.1700
Data Index: 2916331 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19