Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5273 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0595. Min Range: -3.0595
Max Act: 3.0595. Min Act: -0.1699
Data Index: 7422845 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.9013. Min Act: -0.1700
Data Index: 6306109 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8696. Min Act: -0.1700
Data Index: 63360 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 7503322 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 5625474 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 5621049 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 3565539 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 6502807 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 6418354 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8537. Min Act: -0.1700
Data Index: 8754097 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 212463 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 8061162 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 4115176 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8378. Min Act: -0.1700
Data Index: 4504381 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8219. Min Act: -0.1700
Data Index: 2223553 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.7901. Min Act: -0.1700
Data Index: 5429869 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.7901. Min Act: -0.1700
Data Index: 6012861 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.7901. Min Act: -0.1700
Data Index: 142847 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8060. Min Act: -0.1700
Data Index: 6756859 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0595. Min Range: -3.0595
Max Act: 2.8060. Min Act: -0.1700
Data Index: 4025424 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19