Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.5625. Min Act: -0.1700
Data Index: 2192424 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.3750. Min Act: -0.1700
Data Index: 4812324 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.3438. Min Act: -0.1700
Data Index: 4107469 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.3438. Min Act: -0.1700
Data Index: 6775702 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.3125. Min Act: -0.1700
Data Index: 1352972 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.2500. Min Act: -0.1700
Data Index: 6128777 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.2500. Min Act: -0.1700
Data Index: 4652292 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.1563. Min Act: -0.1700
Data Index: 3686786 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.1563. Min Act: -0.1700
Data Index: 4340737 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.1250. Min Act: -0.1700
Data Index: 8727486 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0938. Min Act: -0.1700
Data Index: 3236622 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0938. Min Act: -0.1700
Data Index: 8607447 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0625. Min Act: -0.1700
Data Index: 3395286 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0313. Min Act: -0.1700
Data Index: 5914968 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0625. Min Act: -0.1700
Data Index: 531176 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0313. Min Act: -0.1700
Data Index: 3147060 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0313. Min Act: -0.1700
Data Index: 7773526 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5625. Min Range: -7.5625
Max Act: 6.9688. Min Act: -0.1700
Data Index: 352647 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0000. Min Act: -0.1700
Data Index: 3975647 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5625. Min Range: -7.5625
Max Act: 7.0000. Min Act: -0.1700
Data Index: 5100276 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19