Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.4844. Min Act: -0.1700
Data Index: 2945977 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.2656. Min Act: -0.1700
Data Index: 8776508 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.1719. Min Act: -0.1700
Data Index: 953696 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.1406. Min Act: -0.1700
Data Index: 622210 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.1094. Min Act: -0.1700
Data Index: 3180369 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0781. Min Act: -0.1700
Data Index: 1410214 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0781. Min Act: -0.1700
Data Index: 4288990 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0781. Min Act: -0.1700
Data Index: 4409625 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0469. Min Act: -0.1700
Data Index: 3732204 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0469. Min Act: -0.1700
Data Index: 7196510 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0469. Min Act: -0.1700
Data Index: 835768 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0469. Min Act: -0.1700
Data Index: 8622019 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0469. Min Act: -0.1700
Data Index: 883294 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0469. Min Act: -0.1700
Data Index: 6211527 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0156. Min Act: -0.1700
Data Index: 5008008 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0156. Min Act: -0.1700
Data Index: 5008009 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0156. Min Act: -0.1700
Data Index: 5008007 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4844. Min Range: -5.4844
Max Act: 5.0156. Min Act: -0.1700
Data Index: 460505 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4844. Min Range: -5.4844
Max Act: 4.9844. Min Act: -0.1700
Data Index: 8437259 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4844. Min Range: -5.4844
Max Act: 4.9844. Min Act: -0.1700
Data Index: 3561840 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19