Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.7246. Min Act: -0.1700
Data Index: 6306935 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.8496. Min Act: -0.1700
Data Index: 6443750 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.2871. Min Act: -0.1700
Data Index: 8698919 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.3496. Min Act: -0.1700
Data Index: 6395855 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.2871. Min Act: -0.1700
Data Index: 2276476 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.2871. Min Act: -0.1700
Data Index: 8612240 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.2246. Min Act: -0.1700
Data Index: 50541 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.0996. Min Act: -0.1700
Data Index: 8312669 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8496. Min Range: -8.8496
Max Act: 8.0996. Min Act: -0.1700
Data Index: 517008 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.9746. Min Act: -0.1700
Data Index: 4905975 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.9746. Min Act: -0.1700
Data Index: 1710761 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.9746. Min Act: -0.1700
Data Index: 5677426 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.8496. Min Act: -0.1700
Data Index: 2604078 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.8496. Min Act: -0.1700
Data Index: 7366182 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.7871. Min Act: -0.1700
Data Index: 1736041 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.7246. Min Act: -0.1700
Data Index: 1444148 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.5996. Min Act: -0.1700
Data Index: 4874083 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.6621. Min Act: -0.1700
Data Index: 5197789 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.6621. Min Act: -0.1700
Data Index: 7266103 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8496. Min Range: -8.8496
Max Act: 7.6621. Min Act: -0.1700
Data Index: 7885133 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19