Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5848 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.6657. Min Act: -0.1700
Data Index: 6396874 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5095. Min Act: -0.1700
Data Index: 5868723 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.4470. Min Act: -0.1700
Data Index: 3644932 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.2595. Min Act: -0.1700
Data Index: 8224401 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.2907. Min Act: -0.1700
Data Index: 3602041 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1970. Min Act: -0.1700
Data Index: 7501276 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.2282. Min Act: -0.1700
Data Index: 4047948 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.2282. Min Act: -0.1700
Data Index: 2509438 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1657. Min Act: -0.1700
Data Index: 953011 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1657. Min Act: -0.1700
Data Index: 4010204 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1657. Min Act: -0.1700
Data Index: 2773658 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1657. Min Act: -0.1700
Data Index: 5638802 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1345. Min Act: -0.1700
Data Index: 5797902 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1345. Min Act: -0.1700
Data Index: 1482381 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1345. Min Act: -0.1700
Data Index: 428304 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1345. Min Act: -0.1700
Data Index: 5527682 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.0720. Min Act: -0.1700
Data Index: 8250032 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.1032. Min Act: -0.1700
Data Index: 6608056 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.0720. Min Act: -0.1700
Data Index: 854470 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.0720. Min Act: -0.1700
Data Index: 5329291 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19