Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5491 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0902. Min Range: -5.0902
Max Act: 5.0902. Min Act: -0.1700
Data Index: 1150763 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0902. Min Range: -5.0902
Max Act: 5.0902. Min Act: -0.1700
Data Index: 6825171 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0902. Min Range: -5.0902
Max Act: 5.0277. Min Act: -0.1700
Data Index: 2617773 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0902. Min Range: -5.0902
Max Act: 5.0277. Min Act: -0.1700
Data Index: 5862138 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9964. Min Act: -0.1700
Data Index: 6585254 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9964. Min Act: -0.1700
Data Index: 4453917 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9964. Min Act: -0.1700
Data Index: 4996630 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9964. Min Act: -0.1700
Data Index: 3440449 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9964. Min Act: -0.1700
Data Index: 820281 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9339. Min Act: -0.1700
Data Index: 7245991 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9339. Min Act: -0.1700
Data Index: 547391 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9339. Min Act: -0.1700
Data Index: 7225360 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9652. Min Act: -0.1700
Data Index: 4688287 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9027. Min Act: -0.1700
Data Index: 6266570 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9027. Min Act: -0.1700
Data Index: 5191148 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9027. Min Act: -0.1700
Data Index: 7497556 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9027. Min Act: -0.1700
Data Index: 4294215 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.9027. Min Act: -0.1700
Data Index: 1571586 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.8714. Min Act: -0.1700
Data Index: 2604756 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0902. Min Range: -5.0902
Max Act: 4.8714. Min Act: -0.1700
Data Index: 6659453 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19