Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5058 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0605. Min Range: -4.0605
Max Act: 4.0605. Min Act: -0.1700
Data Index: 3385742 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.8730. Min Act: -0.1700
Data Index: 4227625 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.7479. Min Act: -0.1700
Data Index: 6760097 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.7166. Min Act: -0.1700
Data Index: 4296591 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.6540. Min Act: -0.1700
Data Index: 4613468 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.6540. Min Act: -0.1700
Data Index: 3955984 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.6384. Min Act: -0.1700
Data Index: 1261974 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.6540. Min Act: -0.1700
Data Index: 4551849 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5914. Min Act: -0.1700
Data Index: 7223476 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5601. Min Act: -0.1700
Data Index: 3055267 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5601. Min Act: -0.1700
Data Index: 6625908 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5444. Min Act: -0.1700
Data Index: 8517485 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5601. Min Act: -0.1700
Data Index: 4660695 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5444. Min Act: -0.1700
Data Index: 5457456 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5444. Min Act: -0.1700
Data Index: 8007711 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5288. Min Act: -0.1700
Data Index: 2605766 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5288. Min Act: -0.1700
Data Index: 2015218 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5444. Min Act: -0.1700
Data Index: 4428151 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5444. Min Act: -0.1700
Data Index: 103036 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0605. Min Range: -4.0605
Max Act: 3.5444. Min Act: -0.1700
Data Index: 8127147 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19